Deep learning has shown remarkable success in remote sensing change detection (CD), aiming to identify semantic change regions between co-registered satellite image pairs acquired at distinct time stamps. However, existing convolutional neural network (CNN) and transformer-based frameworks often struggle to accurately segment semantic change regions. Moreover, transformers-based methods with standard self-attention suffer from quadratic computational complexity with respect to the image resolution, making them less practical for CD tasks with limited training data. To address these issues, we propose an efficient change detection (CD) framework, efficient global and local context aggregation network (ELGC-Net), which leverages rich contextual information to precisely estimate change regions while reducing the model size. Our ELGC-Net comprises a Siamese encoder, fusion modules, and a decoder. The focus of our design is the introduction of an efficient local-global context aggregator (ELGCA) module within the encoder, capturing enhanced global context and local spatial information through a novel pooled-transpose (PT) attention and depthwise convolution, respectively. The PT attention employs pooling operations for robust feature extraction and minimizes computational cost with transposed attention. Extensive experiments on three challenging CD datasets demonstrate that ELGC-Net outperforms existing methods. Compared to the recent transformer-based CD approach (ChangeFormer), ELGC-Net achieves a 1.4% gain in intersection over union (IoU) metric on the LEVIR-CD dataset, while significantly reducing trainable parameters. Our proposed ELGC-Net sets a new state-of-the-art (SOTA) performance in remote sensing CD benchmarks. Finally, we also introduce ELGC-Net-LW, a lighter variant with significantly reduced computational complexity, suitable for resource-constrained settings, while achieving comparable performance.

Anomaly detection has recently gained increasing attention in the field of computer vision, likely due to its broad set of applications ranging from product fault detection on industrial production lines and impending event detection in video surveillance to finding lesions in medical scans. Regardless of the domain, anomaly detection is typically framed as a one-class classification task, where the learning is conducted on normal examples only. An entire family of successful anomaly detection methods is based on learning to reconstruct masked normal inputs (e.g. patches, future frames, etc.) and exerting the magnitude of the reconstruction error as an indicator for the abnormality level. Unlike other reconstruction-based methods, we present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level. The proposed self-supervised block is extremely flexible, enabling information masking at any layer of a neural network and being compatible with a wide range of neural architectures. In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss. Furthermore, we show that our block is applicable to a wider variety of tasks, adding anomaly detection in medical images and thermal videos to the previously considered tasks based on RGB images and surveillance videos. We exhibit the generality and flexibility of SSMCTB by integrating it into multiple state-of-the-art neural models for anomaly detection, bringing forth empirical results that confirm considerable performance improvements on five benchmarks: MVTec AD, BRATS, Avenue, ShanghaiTech, and Thermal Rare Event.

Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of zero-shot setting. When multiple objects occur jointly in a single image, a critical question is how to effectively fuse multi-class information. In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embeddings. To the best of our knowledge, our work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on three zero-shot benchmarks: NUS-WIDE, Open Images and MS COCO. Furthermore, we show the generalization capabilities of our fusion approach in the zero-shot detection task on MS COCO, achieving favorable performance against existing methods.

Given the often enormous effort required to train GANs, both computationally as well as in dataset collection, the re-use of pretrained GANs largely increases the potential impact of generative models. Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs. This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain. Mining effectively steers GAN sampling towards suitable regions of the latent space, which facilitates the posterior finetuning and avoids pathologies of other methods, such as mode collapse and lack of flexibility. Furthermore, to prevent overfitting on small target domains, we introduce sparse subnetwork selection, that restricts the set of trainable neurons to those that are relevant for the target dataset. We perform comprehensive experiments on several challenging datasets using various GAN architectures (BigGAN, Progressive GAN, and StyleGAN) and show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods. In addition, MineGAN can successfully transfer knowledge from multiple pretrained GANs. MineGAN.

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to robustify the model. In contrast to existing adversarial training methods that only use class-boundary information (e.g., using a cross-entropy loss), we propose to exploit additional information from the feature space to craft stronger adversaries that are in turn used to learn a robust model. Specifically, we use the style and content information of the target sample from another class, alongside its class-boundary information to create adversarial perturbations. We apply our proposed multi-task objective in a deeply supervised manner, extracting multi-scale feature knowledge to create maximally separating adversaries. Subsequently, we propose a max-margin adversarial training approach that minimizes the distance between source image and its adversary and maximizes the distance between the adversary and the target image. Our adversarial training approach demonstrates strong robustness compared to state-of-the-art defenses, generalizes well to naturally occurring corruptions and data distributional shifts, and retains the models accuracy on clean examples.

We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to noncontrast CT scans and the other way around. Solving this task has two important applications: (i) to automatically generate contrast CT scans for patients for whom injecting contrast substance is not an option, and (ii) to enhance the alignment between contrast and non-contrast CT by reducing the differences induced by the contrast substance before registration.Our approach is based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran. Our neural model can be trained on unpaired images, due to the integration of a multi-level cycleconsistency loss. Aside from the standard cycle-consistency loss applied at the image level, we propose to apply additional cycle-consistency losses between intermediate feature representations, which enforces the model to be cycle-consistent at multiple representations levels, leading to superior results. To deal with high-resolution images, we design a hybrid architecture based on convolutional and multi-head attention layers. In addition, we introduce a novel data set, Coltea-Lung-CT-100W, containing 100 3D triphasic lung CT scans (with a total of 37,290 images) collected from 100 female patients (there is one examination per patient). Each scan contains three phases (non-contrast, early portal venous, and late arterial), allowing us to perform experiments to compare our novel approach with state-of-the-art methods for image style transfer.Our empirical results show that CyTran outperforms all competing methods. Moreover, we show that CyTran can be employed as a preliminary step to improve a state-of-the-art medical image alignment method. We release our novel model and data set as open source at: https://github.com/ristea/cycletransformer.Our qualitative and subjective human evaluations reveal that CyTran is the only approach that does not introduce visual artifacts during the translation process. We believe this is a key advantage in our application domain, where medical images need to precisely represent the scanned body parts. (c) 2023 Elsevier B.V. All rights reserved.

We propose a fast single-stage method for both image and video instance segmentation, called SipMask, that preserves the instance spatial information by performing multiple sub-region mask predictions. The main module in our method is a light-weight spatial preservation (SP) module that generates a separate set of spatial coefficients for the sub-regions within a bounding-box, enabling a better delineation of spatially adjacent instances. To better correlate mask prediction with object detection, we further propose a mask alignment weighting loss and a feature alignment scheme. In addition, we identify two issues that impede the performance of single-stage instance segmentation and introduce two modules, including a sample selection scheme and an instance refinement module, to address these two issues. Experiments are performed on both image instance segmentation dataset MS COCO and video instance segmentation dataset YouTube-VIS. On MS COCO test-dev set, our method achieves a state-of-the-art performance. In terms of real-time capabilities, it outperforms YOLACT by a gain of 3.0% (mask AP) under the similar settings, while operating at a comparable speed. On YouTube-VIS validation set, our method also achieves promising results. The source code is available at https://github.com/JialeCao001/SipMask.

In recent years, Siamese network based trackers have significantly advanced the state-of-the-art in real-time tracking. Despite their success, Siamese trackers tend to suffer from high memory costs, which restrict their applicability to mobile devices with tight memory budgets. To address this issue, we propose a distilled Siamese tracking framework to learn small, fast and accurate trackers (students), which capture critical knowledge from large Siamese trackers (teachers) by a teacher-students knowledge distillation model. This model is intuitively inspired by the one teacher versus multiple students learning method typically employed in schools. In particular, our model contains a single teacher-student distillation module and a student-student knowledge sharing mechanism. The former is designed using a tracking-specific distillation strategy to transfer knowledge from a teacher to students. The latter is utilized for mutual learning between students to enable in-depth knowledge understanding. Extensive empirical evaluations on several popular Siamese trackers demonstrate the generality and effectiveness of our framework. Moreover, the results on five tracking benchmarks show that the proposed distilled trackers achieve compression rates of up to 18x and frame-rates of 265 FPS, while obtaining comparable tracking accuracy compared to base models.

Adversarial training (AT) is an effective approach to making deep neural networks robust against adversarial attacks. Recently, different AT defenses are proposed that not only maintain a high clean accuracy but also show significant robustness against popular and well-studied adversarial attacks, such as projected gradient descent (PGD). High adversarial robustness can also arise if an attack fails to find adversarial gradient directions, a phenomenon known as "gradient masking." In this work, we analyze the effect of label smoothing on AT as one of the potential causes of gradient masking. We then develop a guided mechanism to avoid local minima during attack optimization, leading to a novel attack dubbed guided projected gradient attack (G-PGA). Our attack approach is based on a "match and deceive" loss that finds optimal adversarial directions through guidance from a surrogate model. Our modified attack does not require random restarts a large number of attack iterations or a search for optimal step size. Furthermore, our proposed G-PGA is generic, thus it can be combined with an ensemble attack strategy as we demonstrate in the case of auto-attack, leading to efficiency and convergence speed improvements. More than an effective attack, G-PGA can be used as a diagnostic tool to reveal elusive robustness due to gradient masking in adversarial defenses.

Nowadays, airline ticket prices can vary dynamically and significantly for the same flight, even for nearby seats within the same cabin. Customers are seeking to get the lowest price while airlines are trying to keep their overall revenue as high as possible and maximize their profit. Airlines use various kinds of computational techniques to increase their revenue such as demand prediction and price discrimination. From the customer side, two kinds of models are proposed by different researchers to save money for customers: models that predict the optimal time to buy a ticket and models that predict the minimum ticket price. In this paper, we present a review of customer side and airlines side prediction models. Our review analysis shows that models on both sides rely on limited set of features such as historical ticket price data, ticket purchase date and departure date. Features extracted from external factors such as social media data and search engine query are not considered. Therefore, we introduce and discuss the concept of using social media data for ticket/demand prediction. (c) 2019 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Generally, convolutional neural networks (CNNs) process data on a regular grid, e.g. data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open research problem with numerous applications in autonomous driving, robotics, and surveillance. In this paper, we propose an algebraically-constrained normalized convolution layer for CNNs with highly sparse input that has a smaller number of network parameters compared to related work. We propose novel strategies for determining the confidence from the convolution operation and propagating it to consecutive layers. We also propose an objective function that simultaneously minimizes the data error while maximizing the output confidence. To integrate structural information, we also investigate fusion strategies to combine depth and RGB information in our normalized convolution network framework. In addition, we introduce the use of output confidence as an auxiliary information to improve the results. The capabilities of our normalized convolution network framework are demonstrated for the problem of scene depth completion. Comprehensive experiments are performed on the KITTI-Depth and the NYU-Depth-v2 datasets. The results clearly demonstrate that the proposed approach achieves superior performance while requiring only about 1-5% of the number of parameters compared to the state-of-the-art methods.

Generic visual tracking is a challenging computer vision problem, with numerous applications. Most existing approaches rely on appearance information by employing either hand-crafted features or deep RGB features extracted from convolutional neural networks. Despite their success, these approaches struggle in case of ambiguous appearance information, leading to tracking failure. In such cases, we argue that motion cue provides discriminative and complementary information that can improve tracking performance. Contrary to visual tracking, deep motion features have been successfully applied for action recognition and video classification tasks. Typically, the motion features are learned by training a CNN on optical flow images extracted from large amounts of labeled videos. In this paper, we investigate the impact of deep motion features in a tracking-by-detection framework. We also evaluate the fusion of hand-crafted, deep RGB, and deep motion features and show that they contain complementary information. To the best of our knowledge, we are the first to propose fusing appearance information with deep motion features for visual tracking. Comprehensive experiments clearly demonstrate that our fusion approach with deep motion features outperforms standard methods relying on appearance information alone.

Color description is one of the fundamental problems of image understanding. One of the popular ways to represent colors is by means of color names. Most existing work on color names focuses on only the eleven basic color terms of the English language. This could be limiting the discriminative power of these representations, and representations based on more color names are expected to perform better. However, there exists no clear strategy to choose additional color names. We collect a dataset of 28 additional color names. To ensure that the resulting color representation has high discriminative power we propose a method to order the additional color names according to their complementary nature with the basic color names. This allows us to compute color name representations with high discriminative power of arbitrary length. In the experiments we show that these new color name descriptors outperform the existing color name descriptor on the task of visual tracking, person re-identification and image classification.

Accurate scale estimation of a target is a challenging research problem in visual object tracking. Most state-of-the-art methods employ an exhaustive scale search to estimate the target size. The exhaustive search strategy is computationally expensive and struggles when encountered with large scale variations. This paper investigates the problem of accurate and robust scale estimation in a tracking-by-detection framework. We propose a novel scale adaptive tracking approach by learning separate discriminative correlation filters for translation and scale estimation. The explicit scale filter is learned online using the target appearance sampled at a set of different scales. Contrary to standard approaches, our method directly learns the appearance change induced by variations in the target scale. Additionally, we investigate strategies to reduce the computational cost of our approach. Extensive experiments are performed on the OTB and the VOT2014 datasets. Compared to the standard exhaustive scale search, our approach achieves a gain of 2.5 percent in average overlap precision on the OTB dataset. Additionally, our method is computationally efficient, operating at a 50 percent higher frame rate compared to the exhaustive scale search. Our method obtains the top rank in performance by outperforming 19 state-of-the-art trackers on OTB and 37 state-of-the-art trackers on VOT2014.

Describing textures is a challenging problem in computer vision and pattern recognition. The classification problem involves assigning a category label to the texture class it belongs to. Several factors such as variations in scale, illumination and viewpoint make the problem of texture description extremely challenging. A variety of histogram based texture representations exists in literature. However, combining multiple texture descriptors and assessing their complementarity is still an open research problem. In this paper, we first show that combining multiple local texture descriptors significantly improves the recognition performance compared to using a single best method alone. This gain in performance is achieved at the cost of high-dimensional final image representation. To counter this problem, we propose to use an information-theoretic compression technique to obtain a compact texture description without any significant loss in accuracy. In addition, we perform a comprehensive evaluation of pure color descriptors, popular in object recognition, for the problem of texture classification. Experiments are performed on four challenging texture datasets namely, KTH-TIPS-2a, KTH-TIPS-2b, FMD and Texture-10. The experiments clearly demonstrate that our proposed compact multi-texture approach outperforms the single best texture method alone. In all cases, discriminative color names outperforms other color features for texture classification. Finally, we show that combining discriminative color names with compact texture representation outperforms state-of-the-art methods by 7.8%,4.3%7.8%,4.3% and 5.0%5.0% on KTH-TIPS-2a, KTH-TIPS-2b and Texture-10 datasets respectively.

Person description is a challenging problem in computer vision. We investigated two major aspects of person description: 1) gender and 2) action recognition in still images. Most state-of-the-art approaches for gender and action recognition rely on the description of a single body part, such as face or full-body. However, relying on a single body part is suboptimal due to significant variations in scale, viewpoint, and pose in real-world images. This paper proposes a semantic pyramid approach for pose normalization. Our approach is fully automatic and based on combining information from full-body, upper-body, and face regions for gender and action recognition in still images. The proposed approach does not require any annotations for upper-body and face of a person. Instead, we rely on pretrained state-of-the-art upper-body and face detectors to automatically extract semantic information of a person. Given multiple bounding boxes from each body part detector, we then propose a simple method to select the best candidate bounding box, which is used for feature extraction. Finally, the extracted features from the full-body, upper-body, and face regions are combined into a single representation for classification. To validate the proposed approach for gender recognition, experiments are performed on three large data sets namely: 1) human attribute; 2) head-shoulder; and 3) proxemics. For action recognition, we perform experiments on four data sets most used for benchmarking action recognition in still images: 1) Sports; 2) Willow; 3) PASCAL VOC 2010; and 4) Stanford-40. Our experiments clearly demonstrate that the proposed approach, despite its simplicity, outperforms state-of-the-art methods for gender and action recognition.

Magnetic resonance imaging (MRI) is a slow diagnostic technique due to its time-consuming acquisition speed. To address this, parallel imaging and compressed sensing methods were developed. Parallel imaging acquires multiple anatomy views simultaneously, while compressed sensing acquires fewer samples than traditional methods. However, reconstructing images from undersampled multi-coil data remains challenging. Existing methods concatenate input slices and adjacent slices along the channel dimension to gather more information for MRI reconstruction. Implicit feature alignment within adjacent slices is crucial for optimal reconstruction performance. Hence, we propose MFormer: an accelerated MRI reconstruction transformer with cascading MFormer blocks containing multi-scale Dynamic Deformable Swin Transformer (DST) modules. Unlike other methods, our DST modules implicitly align adjacent slice features using dynamic deformable convolution and extract local non-local features before merging information. We adapt input variations by aggregating deformable convolution kernel weights and biases through a dynamic weight predictor. Extensive experiments on Stanford2D, Stanford3D, and large-scale FastMRI datasets show the merits of our contributions, achieving state-of-the-art MRI reconstruction performance. Our code and models are available at https://github.com/wafaAlghallabi/MFomer.

3D instance segmentation has recently garnered increased attention. Typical deep learning methods adopt point grouping schemes followed by hand-designed geometric clustering. Inspired by the success of transformers for various 3D tasks, newer hybrid approaches have utilized transformer decoders coupled with convolutional backbones that operate on voxelized scenes. However, due to the nature of sparse feature backbones, the extracted features provided to the transformer decoder are lacking in spatial understanding. Thus, such approaches often predict spatially separate objects as single instances. To this end, we introduce a novel approach for 3D point clouds instance segmentation that addresses the challenge of generating distinct instance masks for objects that share similar appearances but are spatially separated. Our method leverages spatial and semantic supervision with query refinement to improve the performance of hybrid 3D instance segmentation models. Specifically, we provide the transformer block with spatial features to facilitate differentiation between similar object queries and incorporate semantic supervision to enhance prediction accuracy based on object class. Our proposed approach outperforms existing methods on the validation sets of ScanNet V2 and ScanNet200 datasets, establishing a new state-of-the-art for this task.

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. Conventionally trained using the task-specific objective, i.e., cross-entropy loss, prompts tend to overfit downstream data distributions and find it challenging to capture task-agnostic general features from the frozen CLIP. This leads to the loss of the model's original generalization capability. To address this issue, our work introduces a self-regularization framework for prompting called PromptSRC (Prompting with Self-regulating Constraints). PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations using a three-pronged approach by: (a) regulating prompted representations via mutual agreement maximization with the frozen model, (b) regulating with selfensemble of prompts over the training trajectory to encode their complementary strengths, and (c) regulating with textual diversity to mitigate sample diversity imbalance with the visual branch. To the best of our knowledge, this is the first regularization framework for prompt learning that avoids overfitting by jointly attending to pre-trained model features, the training trajectory during prompting, and the textual diversity. PromptSRC explicitly steers the prompts to learn a representation space that maximizes performance on downstream tasks without compromising CLIP generalization. We perform extensive experiments on 4 benchmarks where PromptSRC overall performs favorably well compared to the existing methods. Our code and pre-trained models are publicly available at: https://github.com/muzairkhattak/PromptSRC.

Accurate 3D mitochondria instance segmentation in electron microscopy (EM) is a challenging problem and serves as a prerequisite to empirically analyze their distributions and morphology. Most existing approaches employ 3D convolutions to obtain representative features. However, these convolution-based approaches struggle to effectively capture long-range dependencies in the volume mitochondria data, due to their limited local receptive field. To address this, we propose a hybrid encoder-decoder framework based on a split spatio-temporal attention module that efficiently computes spatial and temporal self-attentions in parallel, which are later fused through a deformable convolution. Further, we introduce a semantic foreground-background adversarial loss during training that aids in delineating the region of mitochondria instances from the background clutter. Our extensive experiments on three benchmarks, Lucchi, MitoEM-R and MitoEM-H, reveal the benefits of the proposed contributions achieving state-of-the-art results on all three datasets. Our code and models are available at https://github.com/ OmkarThawakar/STT- UNET.

It is imperative to ensure the robustness of deep learning models in critical applications such as, healthcare. While recent advances in deep learning have improved the performance of volumetric medical image segmentation models, these models cannot be deployed for real-world applications immediately due to their vulnerability to adversarial attacks. We present a 3D frequency domain adversarial attack for volumetric medical image segmentation models and demonstrate its advantages over conventional input or voxel domain attacks. Using our proposed attack, we introduce a novel frequency domain adversarial training approach for optimizing a robust model against voxel and frequency domain attacks. Moreover, we propose frequency consistency loss to regulate our frequency domain adversarial training that achieves a better tradeoff between model's performance on clean and adversarial samples. Code is available at https://github.com/asif-hanif/vafa.

Burst image processing is becoming increasingly popular in recent years. However, it is a challenging task since individual burst images undergo multiple degradations and often have mutual misalignments resulting in ghosting and zipper artifacts. Existing burst restoration methods usually do not consider the mutual correlation and non-local contextual information among burst frames, which tends to limit these approaches in challenging cases. Another key challenge lies in the robust up-sampling of burst frames. The existing up-sampling methods cannot effectively utilize the advantages of single-stage and progressive up-sampling strategies with conventional and/or recent up-samplers at the same time. To address these challenges, we propose a novel Gated Multi-Resolution Transfer Network (GMTNet) to reconstruct a spatially precise high-quality image from a burst of low-quality raw images. GMT-Net consists of three modules optimized for burst processing tasks: Multi-scale Burst Feature Alignment (MBFA) for feature denoising and alignment, Transposed-Attention Feature Merging (TAFM) for multi-frame feature aggregation, and Resolution Transfer Feature Up-sampler (RTFU) to up-scale merged features and construct a high-quality output image. Detailed experimental analysis on five datasets validate our approach and sets a state-of-the-art for burst super-resolution, burst denoising, and low-light burst enhancement. Our codes and models are available at https://github.com/nanmehta/GMTNet.

Deep neural networks (DNNs) have enabled astounding progress in several vision-based problems. Despite showing high predictive accuracy, recently, several works have revealed that they tend to provide overconfident predictions and thus are poorly calibrated. The majority of the works addressing the miscalibration of DNNs fall under the scope of classification and consider only in-domain predictions. However, there is little to no progress in studying the calibration of DNN-based object detection models, which are central to many vision-based safety-critical applications. In this paper, inspired by the train-time calibration methods, we propose a novel auxiliary loss formulation that explicitly aims to align the class confidence of bounding boxes with the accurateness of predictions (i.e. precision). Since the original formulation of our loss depends on the counts of true positives and false positives in a mini-batch, we develop a differentiable proxy of our loss that can be used during training with other application-specific loss functions. We perform extensive experiments on challenging in-domain and out-domain scenarios with six benchmark datasets including MS-COCO, Cityscapes, Sim10k, and BDD100k. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios. Our source code and pre-trained models are available at https://github.com/akhtarvision/bpc_calibration

Although existing semi-supervised learning models achieve remarkable success in learning with unannotated in-distribution data, they mostly fail to learn on unlabeled data sampled from novel semantic classes due to their closed-set assumption. In this work, we target a pragmatic but under-explored Generalized Novel Category Discovery (GNCD) setting. The GNCD setting aims to categorize unlabeled training data coming from known and novel classes by leveraging the information of partially labeled known classes. We propose a two-stage Contrastive Affinity Learning method with auxiliary visual Prompts, dubbed PromptCAL, to address this challenging problem. Our approach discovers reliable pairwise sample affinities to learn better semantic clustering of both known and novel classes for the class token and visual prompts. First, we propose a discriminative prompt regularization loss to reinforce semantic discriminativeness of prompt-adapted pre-trained vision transformer for refined affinity relationships. Besides, we propose contrastive affinity learning to calibrate semantic representations based on our iterative semi-supervised affinity graph generation method for semantically-enhanced supervision. Extensive experimental evaluation demonstrates that our PromptCAL method is more effective in discovering novel classes even with limited annotations and surpasses the current state-of-the-art on generic and fine-grained benchmarks (e.g., with nearly 11% gain on CUB-200, and 9% on ImageNet-100) on overall accuracy. Our code is available at https: // github.com/ sheng- eatamath / PromptCAL.

Most previous co-salient object detection works mainly focus on extracting co-salient cues via mining the consistency relations across images while ignore explicit exploration of background regions. In this paper, we propose a Discriminative co-saliency and background Mining Transformer framework (DMT) based on several economical multi-grained correlation modules to explicitly mine both co-saliency and background information and effectively model their discrimination. Specifically, we first propose a region-to-region correlation module for introducing inter-image relations to pixel-wise segmentation features while maintaining computational efficiency. Then, we use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation and co-saliency token-to-token correlation modules. We also design a token-guided feature refinement module to enhance the discriminability of the segmentation features under the guidance of the learned tokens. We perform iterative mutual promotion for the segmentation feature extraction and token construction. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method. The source code is available at: https://github.com/dragonlee258079/DMT.

The pose-guided person image generation task requires synthesizing photorealistic images of humans in arbitrary poses. The existing approaches use generative adversarial networks that do not necessarily maintain realistic textures or need dense correspondences that struggle to handle complex deformations and severe occlusions. In this work, we show how denoising diffusion models can be applied for high-fidelity person image synthesis with strong sample diversity and enhanced mode coverage of the learnt data distribution. Our proposed Person Image Diffusion Model (PIDM) disintegrates the complex transfer problem into a series of simpler forward-backward denoising steps. This helps in learning plausible source-to-target transformation trajectories that result in faithful textures and undistorted appearance details. We introduce a texture diffusion module based on cross-attention to accurately model the correspondences between appearance and pose information available in source and target images. Further, we propose disentangled classifier-free guidance to ensure close resemblance between the conditional inputs and the synthesized output in terms of both pose and appearance information. Our extensive results on two large-scale benchmarks and a user study demonstrate the photorealism of our proposed approach under challenging scenarios. We also show how our generated images can help in downstream tasks. Code is available at https://github.com/ankanbhunia/PIDM.

Following the successful application of vision transformers in multiple computer vision tasks, these models have drawn the attention of the signal processing community. This is because signals are often represented as spectrograms (e.g. through Discrete Fourier Transform) which can be directly provided as input to vision transformers. However, naively applying transformers to spectrograms is suboptimal. Since the axes represent distinct dimensions, i.e. frequency and time, we argue that a better approach is to separate the attention dedicated to each axis. To this end, we propose the Separable Transformer (SepTr), an architecture that employs two transformer blocks in a sequential manner, the first attending to tokens within the same time interval, and the second attending to tokens within the same frequency bin. We conduct experiments on three benchmark data sets, showing that our separable architecture outperforms conventional vision transformers and other state-of-the-art methods. Unlike standard transformers, SepTr linearly scales the number of trainable parameters with the input size, thus having a lower memory footprint. Our code is available as open source at https://github.com/ristea/septr.

State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computations. We argue that such an attention computation ignores the multiscale spatio-temporal feature relationships that are crucial to tackle target appearance deformations in videos. To address this issue, we propose a transformer-based VIS framework, named MS-STS VIS, that comprises a novel multi-scale spatio-temporal split (MS-STS) attention module in the encoder. The proposed MS-STS module effectively captures spatio-temporal feature relationships at multiple scales across frames in a video. We further introduce an attention block in the decoder to enhance the temporal consistency of the detected instances in different frames of a video. Moreover, an auxiliary discriminator is introduced during training to ensure better foreground-background separability within the multiscale spatio-temporal feature space. We conduct extensive experiments on two benchmarks: Youtube-VIS (2019 and 2021). Our MS-STS VIS achieves state-of-the-art performance on both benchmarks. When using the ResNet50 backbone, our MS-STS achieves a mask AP of 50.1%, outperforming the best reported results in literature by 2.7% and by 4.8% at higher overlap threshold of AP75, while being comparable in model size and speed on Youtube-VIS 2019 val. set. When using the Swin Transformer backbone, MS-STS VIS achieves mask AP of 61.0% on Youtube-VIS 2019 val. set.

What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, they generally do not scale well across new domains and novel objects. In this paper, we advocate that existing methods lack a top-down supervision signal governed by human-understandable semantics. For the first time in literature, we demonstrate that Multi-modal Vision Transformers (MViT) trained with aligned image-text pairs can effectively bridge this gap. Our extensive experiments across various domains and novel objects show the state-of-the-art performance of MViTs to localize generic objects in images. Based on the observation that existing MViTs do not include multi-scale feature processing and usually require longer training schedules, we develop an efficient MViT architecture using multi-scale deformable attention and late vision-language fusion. We show the significance of MViT proposals in a diverse range of applications including open-world object detection, salient and camouflage object detection, supervised and self-supervised detection tasks. Further, MViTs can adaptively generate proposals given a specific language query and thus offer enhanced interactability.

Detecting abnormal events in video is commonly framed as a one-class classification task, where training videos contain only normal events, while test videos encompass both normal and abnormal events. In this scenario, anomaly detection is an open-set problem. However, some studies assimilate anomaly detection to action recognition. This is a closed-set scenario that fails to test the capability of systems at detecting new anomaly types. To this end, we propose UBnormal, a new supervised open-set benchmark composed of multiple virtual scenes for video anomaly detection. Unlike existing data sets, we introduce abnormal events annotated at the pixel level at training time, for the first time enabling the use of fully-supervised learning methods for abnormal event detection. To preserve the typical open-set formulation, we make sure to include dis-joint sets of anomaly types in our training and test collections of videos. To our knowledge, UBnormal is the first video anomaly detection benchmark to allow a fair head-to-head comparison between one-class open-set models and supervised closed-set models, as shown in our experiments. Moreover, we provide empirical evidence showing that UB-normal can enhance the performance of a state-of-the-art anomaly detection framework on two prominent data sets, Avenue and ShanghaiTech. Our benchmark is freely available at https://github.com/lilygeorgescu/UBnormal.

Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abnormal test samples. Among the successful approaches for anomaly detection, a distinguished category of methods relies on predicting masked information (e.g. patches, future frames, etc.) and leveraging the reconstruction error with respect to the masked information as an abnormality score. Different from related methods, we propose to integrate the reconstruction-based functionality into a novel self-supervised predictive architectural building block. The proposed self-supervised block is generic and can easily be incorporated into various state-of-the-art anomaly detection methods. Our block starts with a convolutional layer with dilated filters, where the center area of the receptive field is masked. The resulting activation maps are passed through a channel attention module. Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field. We demonstrate the generality of our block by integrating it into several state-of-the-art frameworks for anomaly detection on image and video, providing empirical evidence that shows considerable performance improvements on MVTec AD, Avenue, and ShanghaiTech. We release our code as open source at: https://github.com/ ristea/sspcab.

Deep learning models tend to forget their earlier knowledge while incrementally learning new tasks. This behavior emerges because the parameter updates optimized for the new tasks may not align well with the updates suitable for older tasks. The resulting latent representation mismatch causes forgetting. In this work, we propose ELI: Energy-based Latent Aligner for Incremental Learning, which first learns an energy manifold for the latent representations such that previous task latents will have low energy and the current task latents have high energy values. This learned manifold is used to counter the representational shift that happens during incremental learning. The implicit regularization that is offered by our proposed methodology can be used as a plug-and-play module in existing incremental learning methodologies. We validate this through extensive evaluation on CIFAR-100, ImageNet subset, ImageNet 1k and Pascal VOC datasets. We observe consistent improvement when ELI is added to three prominent methodologies in class-incremental learning, across multiple incremental settings. Further, when added to the state-of-the-art incremental object detector, ELI provides over 5% improvement in detection accuracy, corroborating its effectiveness and complementary advantage to the existing art. Code is available at: https://github.com/JosephKJ/ELI.

Modern handheld devices can acquire burst image sequence in a quick succession. However, the individual acquired frames suffer from multiple degradations and are misaligned due to camera shake and object motions. The goal of Burst Image Restoration is to effectively combine complimentary cues across multiple burst frames to generate high-quality outputs. Towards this goal, we develop a novel approach by solely focusing on the effective information exchange between burst frames, such that the degradations get filtered out while the actual scene details are preserved and enhanced. Our central idea is to create a set of pseudo-burst features that combine complimentary information from all the input burst frames to seamlessly exchange information. However, the pseudo-burst cannot be successfully created unless the individual burst frames are properly aligned to discount interframe movements. Therefore, our approach initially extracts pre-processed features from each burst frame and matches them using an edge-boosting burst alignment module. The pseudo-burst features are then created and enriched using multi-scale contextual information. Our final step is to adaptively aggregate information from the pseudo-burst features to progressively increase resolution in multiple stages while merging the pseudo-burst features. In comparison to existing works that usually follow a late fusion scheme with single-stage upsampling, our approach performs favorably, delivering state-of-the-art performance on burst super-resolution, burst low-light image enhancement and burst denoising tasks. The source code and pre-trained models are available at https://github.com/akshaydudhane16/BIPNet.

Modern digital cameras generally count on image signal processing (ISP) pipelines for producing naturalistic RGB images. Nevertheless, in comparison to DSLR cameras, low-quality images are generally output from portable mobile devices due to their physical limitations. The synthesized low-quality images usually have multiple degradations - low-resolution owing to small camera sensors, mosaic patterns on account of camera filter array and subpixel shifts due to camera motion. Such degradation usually restrain the performance of single image super-resolution methodologies for retrieving high-resolution (HR) image from a single low-resolution (LR) image. Burst image super-resolution aims at restoring a photo-realistic HR image by capturing the abundant information from multiple LR images. Lately, the soaring popularity of burst photography has made multi-frame processing an attractive solution for overcoming the limitations of single image processing. In our work, we thus aim to propose a generic architecture, adaptive feature consolidation network (AFCNet) for multi-frame processing. To alleviate the challenge of effectively modelling the long-range dependency problem, that multi-frame approaches struggle to solve, we utilize encoder-decoder based transformer backbone which learns multi-scale local-global representations. We propose feature alignment module to align LR burst frame features. Further, the aligned features are fused and reconstructed by abridged pseudo-burst fusion module and adaptive group upsampling modules, respectively. Our proposed approach clearly outperforms the other existing state-of-the-art techniques on benchmark datasets. The experimental results illustrate the effectiveness and generality of our proposed framework in upgrading the visual quality of HR images.

Recent progress towards designing models that can generalize to unseen domains (i.e domain generalization) or unseen classes (i.e zero-shot learning) has embarked interest towards building models that can tackle both domain-shift and semantic shift simultaneously (i.e zero-shot domain generalization). For models to generalize to unseen classes in unseen domains, it is crucial to learn feature representation that preserves class-level (domaininvariant) as well as domain-specific information. Motivated from the success of generative zero-shot approaches, we propose a feature generative framework integrated with a COntext COnditional Adaptive (COCOA) Batch-Normalization layer to seamlessly integrate class-level semantic and domain-specific information. The generated visual features better capture the underlying data distribution enabling us to generalize to unseen classes and domains at test-time. We thoroughly evaluate our approach on established large-scale benchmarks - DomainNet, DomainNet-LS (Limited Sources) - as well as a new CUB-Corruptions benchmark, and demonstrate promising performance over baselines and state-of-the-art methods. We show detailed ablations and analysis to verify that our proposed approach indeed allows us to generate better quality visual features relevant for zero-shot domain generalization.

While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen models decisions to a specific targeted class remains a challenging feat. In this paper, we propose a new generative approach for highly transferable targeted perturbations (TTP). We note that the existing methods are less suitable for this task due to their reliance on class-boundary information that changes from one model to another, thus reducing transferability. In contrast, our approach matches the perturbed image distribution with that of the target class, leading to high targeted transferability rates. To this end, we propose a new objective function that not only aligns the global distributions of source and target images, but also matches the local neighbourhood structure between the two domains. Based on the proposed objective, we train a generator function that can adaptively synthesize perturbations specific to a given input. Our generative approach is independent of the source or target domain labels, while consistently performs well against state-of-the-art methods on a wide range of attack settings. As an example, we achieve 32.63% target transferability from (an adversarially weak) VGG19(BN) to (a strong) WideResNet on ImageNet val. set, which is 4x higher than the previous best generative attack and 16x better than instance-specific iterative attack. Code is available at: https://github.com/Muzammal-Naseer/TTP.

Deep neural networks have achieved remarkable performance on a range of classification tasks, with softmax cross-entropy (CE) loss emerging as the de-facto objective function. The CE loss encourages features of a class to have a higher projection score on the true class-vector compared to the negative classes. However, this is a relative constraint and does not explicitly force different class features to be well-separated. Motivated by the observation that ground-truth class representations in CE loss are orthogonal (one-hot encoded vectors), we develop a novel loss function termed `Orthogonal Projection Loss (OPL) which imposes orthogonality in the feature space. OPL augments the properties of CE loss and directly enforces inter-class separation alongside intra-class clustering in the feature space through orthogonality constraints on the mini-batch level. As compared to other alternatives of CE, OPL offers unique advantages e.g., no additional learnable parameters, does not require careful negative mining and is not sensitive to the batch size. Given the plug-and-play nature of OPL, we evaluate it on a diverse range of tasks including image recognition (CIFAR-100), large-scale classification (ImageNet), domain generalization (PACS) and few-shot learning (miniImageNet, CIFAR-FS, tiered-ImageNet and Meta-dataset) and demonstrate its effectiveness across the board. Furthermore, OPL offers better robustness against practical nuisances such as adversarial attacks and label noise. Code is available at: https://github.com/kahnchana/opl.

Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and requires region-specific processing of visual features to preserve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results.

Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosityabout these unknown instances aids in learning about them,when the corresponding knowledge is eventually available.This motivates us to propose a novel computer vision problem called: ‘Open World Object Detection’, where a modelis tasked to: 1) identify objects that have not been introduced to it as ‘unknown’, without explicit supervision to doso, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, whenthe corresponding labels are progressively received. Weformulate the problem, introduce a strong evaluation protocol and provide a novel solution, which we call ORE:Open World Object Detector, based on contrastive clustering and energy based unknown identification. Our experimental evaluation and ablation studies analyse the efficacyof ORE in achieving Open World objectives. As an interesting by-product, we find that identifying and characterisingunknown instances helps to reduce confusion in an incremental object detection setting, where we achieve state-ofthe-art performance, with no extra methodological effort.We hope that our work will attract further research into thisnewly identified, yet crucial research direction.

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock towards their real-world deployment. Transferability of adversarial examples demand generalizable defenses that can provide cross-task protection. Adversarial training that enhances robustness by modifying target model’s parameters lacks such generalizability. On the other hand, different input processing based defenses fall short in the face of continuously evolving attacks. In this paper, we take the first step to combine the benefits of both approaches and propose a self-supervised adversarial training mechanism in the input space. By design, our defense is a generalizable approach and provides significant robustness against the unseen adversarial attacks (\eg by reducing the success rate of translation-invariant ensemble attack from 82.6% to 31.9% in comparison to previous state-of-the-art). It can be deployed as a plug-and-play solution to protect a variety of vision systems, as we demonstrate for the case of classification, segmentation and detection.

One of the attractive characteristics of deep neural networks is their ability to transfer knowledge obtained in one domain to other related domains. As a result, high-quality networks can be trained in domains with relatively little training data. This property has been extensively studied for discriminative networks but has received significantly less attention for generative models. Given the often enormous effort required to train GANs, both computationally as well as in the dataset collection, the re-use of pretrained GANs is a desirable objective. We propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs. This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain. Mining effectively steers GAN sampling towards suitable regions of the latent space, which facilitates the posterior finetuning and avoids pathologies of other methods such as mode collapse and lack of flexibility. We perform experiments on several complex datasets using various GAN architectures (BigGAN, Progressive GAN) and show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods. In addition, MineGAN can successfully transfer knowledge from multiple pretrained GANs. Our code is available at: https://github.com/yaxingwang/MineGAN.

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous meta-learning techniques, our approach is task-agnostic. When presented with a continuum of data, our model automatically identifies the task and quickly adapts to it with just a single update. We perform extensive experiments on five datasets in a class-incremental setting, leading to significant improvements over the state of the art methods (e.g., a 21.3% boost on CIFAR100 with 10 incremental tasks). Specifically, on large-scale datasets that generally prove difficult cases for incremental learning, our approach delivers absolute gains as high as 19.1% and 7.4% on ImageNet and MS-Celeb datasets, respectively.

Convolutional neural networks (CNNs) have recently achieved outstanding results for various vision tasks, including indoor scene understanding. The de facto practice employed by state-of-the-art indoor scene recognition approaches is to use RGB pixel values as input to CNN models that are trained on large amounts of labeled data (Image-Net or Places). Here, we investigate CNN architectures by augmenting RGB images with estimated depth and texture information, as multiple streams, for monocular indoor scene recognition. First, we exploit the recent advancements in the field of depth estimation from monocular images and use the estimated depth information to train a CNN model for learning deep depth features. Second, we train a CNN model to exploit the successful Local Binary Patterns (LBP) by using mapped coded images with explicit LBP encoding to capture texture information available in indoor scenes. We further investigate different fusion strategies to combine the learned deep depth and texture streams with the traditional RGB stream. Comprehensive experiments are performed on three indoor scene classification benchmarks: MIT-67, OCIS and SUN-397. The proposed multi-stream network significantly outperforms the standard RGB network by achieving an absolute gain of 9.3%, 4.7%, 7.3% on the MIT-67, OCIS and SUN-397 datasets respectively.

Single-stage object detectors have recently gained popularity due to their combined advantage of high detection accuracy and real-time speed. However, while promising results have been achieved by these detectors on standard-sized objects, their performance on small objects is far from satisfactory. To detect very small/large objects, classical pyramid representation can be exploited, where an image pyramid is used to build afeature pyramid (featurized image pyramid), enabling detection across a range of scales. Existing single-stage detectors avoid such afeaturized image pyramid representation due to its memory and time complexity. In this paper we introduce a light-weight architecture to efficiently produce featurized image pyramid in a single-stage detection framework. The resulting multi-scale features are then injected into the prediction layers of the detector using an attention module. The performance of our detector is validated on two benchmarks: PASCAL VOC and MS COCO. For a 300 x 300 input, our detector operates at 111 frames per second (FPS) on a Titan X GPU, providing state-of-the-art detection accuracy on PASCAL VOC 2007 testset. On the MS COCO testset, our detector achieves state-of-the-art results surpassing all existing single-stage methods in the case of single-scale inference.

Siamese approaches address the visual tracking problem by extracting an appearance template from the current frame, which is used to localize the target in the next frame. In general, this template is linearly combined with the accumulated template from the previous frame, resulting in an exponential decay of information over time. While such an approach to updating has led to improved results, its simplicity limits the potential gain likely to be obtained by learning to update. Therefore, we propose to replace the handcrafted update function with a method which learns to update. We use a convolutional neural network, called UpdateNet, which given the initial template, the accumulated template and the template of the current frame aims to estimate the optimal template for the next frame. The UpdateNet is compact and can easily be integrated into existing Siamese trackers. We demonstrate the generality of the proposed approach by applying it to two Siamese trackers, SiamFC and DaSiamRPN. Extensive experiments on VOT2016, VOT2018, LaSOT, and TrackingNet datasets demonstrate that our UpdateNet effectively predicts the new target template, outperforming the standard linear update. On the large-scale TrackingNet dataset, our UpdateNet improves the results of DaSiamRPN with an absolute gain of 3.9% in terms of success score. Code and models are available at https://github.com/zhanglichao/updatenet.

While recent years have witnessed astonishing improvements in visual tracking robustness, the advancements in tracking accuracy have been limited. As the focus has been directed towards the development of powerful classifiers, the problem of accurate target state estimation has been largely overlooked. In fact, most trackers resort to a simple multi-scale search in order to estimate the target bounding box. We argue that this approach is fundamentally limited since target estimation is a complex task, requiring highlevel knowledge about the object. We address this problem by proposing a novel tracking architecture, consisting of dedicated target estimation and classification components. High level knowledge is incorporated into the target estimation through extensive offline learning. Our target estimation component is trained to predict the overlap between the target object and an estimated bounding box. By carefully integrating targetspecific information, our approach achieves previously unseen bounding box accuracy. We further introduce a classification component that is trained online to guarantee high discriminative power in the presence of distractors. Our final tracking framework sets a new state-of-the-art on five challenging benchmarks. On the new large-scale TrackingNet dataset, our tracker ATOM achieves a relative gain of 15% over the previous best approach, while running at over 30 FPS. Code and models are available at https://github.com/visionml/pytracking.

One of the fundamental challenges in video object segmentation is to find an effective representation of the target and background appearance. The best performing approaches resort to extensive fine-tuning of a convolutional neural network for this purpose. Besides being prohibitively expensive, this strategy cannot be truly trained end-to-end since the online fine-tuning procedure is not integrated into the offline training of the network. To address these issues, we propose a network architecture that learns a powerful representation of the target and background appearance in a single forward pass. The introduced appearance module learns a probabilistic generative model of target and background feature distributions. Given a new image, it predicts the posterior class probabilities, providing a highly discriminative cue, which is processed in later network modules. Both the learning and prediction stages of our appearance module are fully differentiable, enabling true end-to-end training of the entire segmentation pipeline. Comprehensive experiments demonstrate the effectiveness of the proposed approach on three video object segmentation benchmarks. We close the gap to approaches based on online fine-tuning on DAVIS17, while operating at 15 FPS on a single GPU. Furthermore, our method outperforms all published approaches on the large-scale YouTube-VOS dataset.

In most computer vision applications, convolutional neural networks (CNNs) operate on dense image data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open problem with numerous applications in autonomous driving, robotics, and surveillance. To tackle this challenging problem, we introduce an algebraically-constrained convolution layer for CNNs with sparse input and demonstrate its capabilities for the scene depth completion task. We propose novel strategies for determining the confidence from the convolution operation and propagating it to consecutive layers. Furthermore, we propose an objective function that simultaneously minimizes the data error while maximizing the output confidence. Comprehensive experiments are performed on the KITTI depth benchmark and the results clearly demonstrate that the proposed approach achieves superior performance while requiring three times fewer parameters than the state-of-the-art methods. Moreover, our approach produces a continuous pixel-wise confidence map enabling information fusion, state inference, and decision support.

This paper investigates the problem of position estimation of unmanned surface vessels (USVs) operating in coastal areas or in the archipelago. We propose a position estimation method where the horizon line is extracted in a 360 degree panoramic image around the USV. We design a CNN architecture to determine an approximate horizon line in the image and implicitly determine the camera orientation (the pitch and roll angles). The panoramic image is warped to compensate for the camera orientation and to generate an image from an approximately level camera. A second CNN architecture is designed to extract the pixelwise horizon line in the warped image. The extracted horizon line is correlated with digital elevation model (DEM) data in the Fourier domain using a MOSSE correlation filter. Finally, we determine the location of the maximum correlation score over the search area to estimate the position of the USV. Comprehensive experiments are performed in a field trial in the archipelago. Our approach provides promising results by achieving position estimates with GPS-level accuracy.

Recognizing human attributes in unconstrained environments is a challenging computer vision problem. State-of-the-art approaches to human attribute recognition are based on convolutional neural networks (CNNs). The de facto practice when training these CNNs on a large labeled image dataset is to take RGB pixel values of an image as input to the network. In this work, we propose a two-stream part-based deep representation for human attribute classification. Besides the standard RGB stream, we train a deep network by using mapped coded images with explicit texture information, that complements the standard RGB deep model. To integrate human body parts knowledge, we employ the deformable part-based models together with our two-stream deep model. Experiments are performed on the challenging Human Attributes (HAT-27) Dataset consisting of 27 different human attributes. Our results clearly show that (a) the two-stream deep network provides consistent gain in performance over the standard RGB model and (b) that the attribute classification results are further improved with our two-stream part-based deep representations, leading to state-of-the-art results.

Probabilistic methods for point set registration have demonstrated competitive results in recent years. These techniques estimate a probability distribution model of the point clouds. While such a representation has shown promise, it is highly sensitive to variations in the density of 3D points. This fundamental problem is primarily caused by changes in the sensor location across point sets.    We revisit the foundations of the probabilistic registration paradigm. Contrary to previous works, we model the underlying structure of the scene as a latent probability distribution, and thereby induce invariance to point set density changes. Both the probabilistic model of the scene and the registration parameters are inferred by minimizing the Kullback-Leibler divergence in an Expectation Maximization based framework. Our density-adaptive registration successfully handles severe density variations commonly encountered in terrestrial Lidar applications. We perform extensive experiments on several challenging real-world Lidar datasets. The results demonstrate that our approach outperforms state-of-the-art probabilistic methods for multi-view registration, without the need of re-sampling.

Semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionized the field of image semantic segmentation, its impact on point cloud data has been limited so far. Recent attempts, based on 3D deep learning approaches (3D-CNNs), have achieved below-expected results. Such methods require voxelizations of the underlying point cloud data, leading to decreased spatial resolution and increased memory consumption. Additionally, 3D-CNNs greatly suffer from the limited availability of annotated datasets.

Autonomous driving safety is becoming a paramount issue due to the emergence of many autonomous vehicle prototypes. The safety measures ensure that autonomous vehicles are safe to operate among pedestrians, cyclists and conventional vehicles. While safety measures for pedestrians have been widely studied in literature, little attention has been paid to safety measures for cyclists. Visual cyclists analysis is a challenging problem due to the complex structure and dynamic nature of the cyclists. The dynamic model used for cyclists analysis heavily relies on the wheels. In this paper, we investigate the problem of ellipse detection for visual cyclists analysis in the wild. Our first contribution is the introduction of a new challenging annotated dataset for bicycle wheels, collected in real-world urban environment. Our second contribution is a method that combines reliable arcs selection and grouping strategies for ellipse detection. The reliable selection and grouping mechanism leads to robust ellipse detections when combined with the standard least square ellipse fitting approach. Our experiments clearly demonstrate that our method provides improved results, both in terms of accuracy and robustness in challenging urban environment settings.

Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set. Due to the limited amount of labeled training data, additional samples need to be extracted and labeled by the tracker itself. This often leads to the inclusion of corrupted training samples, due to occlusions, misalignments and other perturbations. Existing tracking-by-detection methods either ignore this problem, or employ a separate component for managing the training set. We propose a novel generic approach for alleviating the problem of corrupted training samples in tracking-by-detection frameworks. Our approach dynamically manages the training set by estimating the quality of the samples. Contrary to existing approaches, we propose a unified formulation by minimizing a single loss over both the target appearance model and the sample quality weights. The joint formulation enables corrupted samples to be down-weighted while increasing the impact of correct ones. Experiments are performed on three benchmarks: OTB-2015 with 100 videos, VOT-2015 with 60 videos, and Temple-Color with 128 videos. On the OTB-2015, our unified formulation significantly improves the baseline, with a gain of 3.8% in mean overlap precision. Finally, our method achieves state-of-the-art results on all three datasets.

Visual object tracking performance has improved significantly in recent years. Most trackers are based on either of two paradigms: online learning of an appearance model or the use of a pre-trained object detector. Methods based on online learning provide high accuracy, but are prone to model drift. The model drift occurs when the tracker fails to correctly estimate the tracked object’s position. Methods based on a detector on the other hand typically have good long-term robustness, but reduced accuracy compared to online methods.

Despite the complementarity of the aforementioned approaches, the problem of fusing them into a single framework is largely unexplored. In this paper, we propose a novel fusion between an online tracker and a pre-trained detector for tracking humans from a UAV. The system operates at real-time on a UAV platform. In addition we present a novel dataset for long-term tracking in a UAV setting, that includes scenarios that are typically not well represented in standard visual tracking datasets.

3D-point set registration is an active area of research in computer vision. In recent years, probabilistic registration approaches have demonstrated superior performance for many challenging applications. Generally, these probabilistic approaches rely on the spatial distribution of the 3D-points, and only recently color information has been integrated into such a framework, significantly improving registration accuracy. Other than local color information, high-dimensional 3D shape features have been successfully employed in many applications such as action recognition and 3D object recognition. In this paper, we propose a probabilistic framework to integrate high-dimensional 3D shape features with color information for point set registration. The 3D shape features are distinctive and provide complementary information beneficial for robust registration. We validate our proposed framework by performing comprehensive experiments on the challenging Stanford Lounge dataset, acquired by a RGB-D sensor, and an outdoor dataset captured by a Lidar sensor. The results clearly demonstrate that our approach provides superior results both in terms of robustness and accuracy compared to state-of-the-art probabilistic methods.

The Thermal Infrared Visual Object Tracking challenge 2016, VOT-TIR2016, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2016 is the second benchmark on short-term tracking in TIR sequences. Results of 24 trackers are presented. For each participating tracker, a short description is provided in the appendix. The VOT-TIR2016 challenge is similar to the 2015 challenge, the main difference is the introduction of new, more difficult sequences into the dataset. Furthermore, VOT-TIR2016 evaluation adopted the improvements regarding overlap calculation in VOT2016. Compared to VOT-TIR2015, a significant general improvement of results has been observed, which partly compensate for the more difficult sequences. The dataset, the evaluation kit, as well as the results are publicly available at the challenge website.

Automatic analysis of visual art, such as paintings, is a challenging inter-disciplinary research problem. Conventional approaches only rely on global scene characteristics by encoding holistic information for computational painting categorization. We argue that such approaches are sub-optimal and that discriminative common visual structures provide complementary information for painting classification. We present an approach that encodes both the global scene layout and discriminative latent common structures for computational painting categorization. The region of interests are automatically extracted, without any manual part labeling, by training class-specific deformable part-based models. Both holistic and region-of-interests are then described using multi-scale dense convolutional features. These features are pooled separately using Fisher vector encoding and concatenated afterwards in a single image representation. Experiments are performed on a challenging dataset with 91 different painters and 13 diverse painting styles. Our approach outperforms the standard method, which only employs the global scene characteristics. Furthermore, our method achieves state-of-the-art results outperforming a recent multi-scale deep features based approach [11] by 6.4% and 3.8% respectively on artist and style classification.

Visual object tracking is a challenging computer vision problem with numerous real-world applications. This paper investigates the impact of convolutional features for the visual tracking problem. We propose to use activations from the convolutional layer of a CNN in discriminative correlation filter based tracking frameworks. These activations have several advantages compared to the standard deep features (fully connected layers). Firstly, they mitigate the need of task specific fine-tuning. Secondly, they contain structural information crucial for the tracking problem. Lastly, these activations have low dimensionality. We perform comprehensive experiments on three benchmark datasets: OTB, ALOV300++ and the recently introduced VOT2015. Surprisingly, different to image classification, our results suggest that activations from the first layer provide superior tracking performance compared to the deeper layers. Our results further show that the convolutional features provide improved results compared to standard handcrafted features. Finally, results comparable to state-of-theart trackers are obtained on all three benchmark datasets.

Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively learned correlation filters (DCF) have been successfully applied to address this problem for tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood. However, the periodic assumption also introduces unwanted boundary effects, which severely degrade the quality of the tracking model.

We propose Spatially Regularized Discriminative Correlation Filters (SRDCF) for tracking. A spatial regularization component is introduced in the learning to penalize correlation filter coefficients depending on their spatial location. Our SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples. We further propose an optimization strategy, based on the iterative Gauss-Seidel method, for efficient online learning of our SRDCF. Experiments are performed on four benchmark datasets: OTB-2013, ALOV++, OTB-2015, and VOT2014. Our approach achieves state-of-the-art results on all four datasets. On OTB-2013 and OTB-2015, we obtain an absolute gain of 8.0% and 8.2% respectively, in mean overlap precision, compared to the best existing trackers.

The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 38 trackers are presented. The number of tested trackers makes VOT 2014 the largest benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the appendix. Features of the VOT2014 challenge that go beyond its VOT2013 predecessor are introduced: (i) a new VOT2014 dataset with full annotation of targets by rotated bounding boxes and per-frame attribute, (ii) extensions of the VOT2013 evaluation methodology, (iii) a new unit for tracking speed assessment less dependent on the hardware and (iv) the VOT2014 evaluation toolkit that significantly speeds up execution of experiments. The dataset, the evaluation kit as well as the results are publicly available at the challenge website (http://​votchallenge.​net).

In this article we provide an overview of color name applications in computer vision. Color names are linguistic labels which humans use to communicate color. Computational color naming learns a mapping from pixels values to color names. In recent years color names have been applied to a wide variety of computer vision applications, including image classification, object recognition, texture classification, visual tracking and action recognition. Here we provide an overview of these results which show that in general color names outperform photometric invariants as a color representation.

Recognizing human actions in still images is a challenging problem in computer vision due to significant amount of scale, illumination and pose variation. Given the bounding box of a person both at training and test time, the task is to classify the action associated with each bounding box in an image. Most state-of-the-art methods use the bag-of-words paradigm for action recognition. The bag-of-words framework employing a dense multi-scale grid sampling strategy is the de facto standard for feature detection. This results in a scale invariant image representation where all the features at multiple-scales are binned in a single histogram. We argue that such a scale invariant strategy is sub-optimal since it ignores the multi-scale information available with each bounding box of a person. This paper investigates alternative approaches to scale coding for action recognition in still images. We encode multi-scale information explicitly in three different histograms for small, medium and large scale visual-words. Our first approach exploits multi-scale information with respect to the image size. In our second approach, we encode multi-scale information relative to the size of the bounding box of a person instance. In each approach, the multi-scale histograms are then concatenated into a single representation for action classification. We validate our approaches on the Willow dataset which contains seven action categories: interacting with computer, photography, playing music, riding bike, riding horse, running and walking. Our results clearly suggest that the proposed scale coding approaches outperform the conventional scale invariant technique. Moreover, we show that our approach obtains promising results compared to more complex state-of-the-art methods.

Visual tracking is a challenging problem in computer vision. Most state-of-the-art visual trackers either rely on luminance information or use simple color representations for image description. Contrary to visual tracking, for object recognition and detection, sophisticated color features when combined with luminance have shown to provide excellent performance. Due to the complexity of the tracking problem, the desired color feature should be computationally efficient, and possess a certain amount of photometric invariance while maintaining high discriminative power.

This paper investigates the contribution of color in a tracking-by-detection framework. Our results suggest that color attributes provides superior performance for visual tracking. We further propose an adaptive low-dimensional variant of color attributes. Both quantitative and attributebased evaluations are performed on 41 challenging benchmark color sequences. The proposed approach improves the baseline intensity-based tracker by 24% in median distance precision. Furthermore, we show that our approach outperforms state-of-the-art tracking methods while running at more than 100 frames per second.

State-of-the-art texture descriptors typically operate on grey scale images while ignoring color information. A common way to obtain a joint color-texture representation is to combine the two visual cues at the pixel level. However, such an approach provides sub-optimal results for texture categorisation task.

In this paper we investigate how to optimally exploit color information for texture recognition. We evaluate a variety of color descriptors, popular in image classification, for texture categorisation. In addition we analyze different fusion approaches to combine color and texture cues. Experiments are conducted on the challenging scenes and 10 class texture datasets. Our experiments clearly suggest that in all cases color names provide the best performance. Late fusion is the best strategy to combine color and texture. By selecting the best color descriptor with optimal fusion strategy provides a gain of 5% to 8% compared to texture alone on scenes and texture datasets.

This work proposes a weakly-supervised temporal action localization framework, called D2-Net, which strives to temporally localize actions using video-level supervision. Our main contribution is the introduction of a novel loss formulation, which jointly enhances the discriminability of latent embeddings and robustness of the output temporal class activations with respect to foreground-background noise caused by weak supervision. The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization. The discriminative term incorporates a classification loss and utilizes a top-down attention mechanism to enhance the separability of latent foreground-background embeddings. The denoising loss term explicitly addresses the foreground-background noise in class activations by simultaneously maximizing intra-video and inter-video mutual information using a bottom-up attention mechanism. As a result, activations in the foreground regions are emphasized whereas those in the background regions are suppressed, thereby leading to more robust predictions. Comprehensive experiments are performed on multiple benchmarks, including THUMOS14 and ActivityNet1.2. Our D2-Net performs favorably in comparison to the existing methods on all datasets, achieving gains as high as 2.3% in terms of mAP at IoU=0.5 on THUMOS14

While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen model's decisions to a specific `targeted' class remains a challenging feat. In this paper, we propose a new generative approach for highly transferable targeted perturbations (\ours). We note that the existing methods are less suitable for this task due to their reliance on class-boundary information that changes from one model to another, thus reducing transferability. In contrast, our approach matches the perturbed image `distribution' with that of the target class, leading to high targeted transferability rates. To this end, we propose a new objective function that not only aligns the global distributions of source and target images, but also matches the local neighbourhood structure between the two domains. Based on the proposed objective, we train a generator function that can adaptively synthesize perturbations specific to a given input. Our generative approach is independent of the source or target domain labels, while consistently performs well against state-of-the-art methods on a wide range of attack settings. As an example, we achieve 32.63% target transferability from (an adversarially weak) VGG19BN to (a strong) WideResNet on ImageNet val. set, which is 4× higher than the previous best generative attack and 16× better than instance-specific iterative attack. 

We propose a novel transformer-based styled handwritten text image generation approach, HWT, that strives to learn both style-content entanglement as well as global and local writing style patterns. The proposed HWT captures the long and short range relationships within the style examples through a self-attention mechanism, thereby encoding both global and local style patterns. Further, the proposed transformer-based HWT comprises an encoder-decoder attention that enables style-content entanglement by gathering the style representation of each query character. To the best of our knowledge, we are the first to introduce a transformer-based generative network for styled handwritten text generation. Our proposed HWT generates realistic styled handwritten text images and significantly outperforms the state-of-the-art demonstrated through extensive qualitative, quantitative and human-based evaluations. The proposed HWT can handle arbitrary length of text and any desired writing style in a few-shot setting. Further, our HWT generalizes well to the challenging scenario where both words and writing style are unseen during training, generating realistic styled handwritten text images.