Search

Automatic Sign Language (SL) recognition is an important task in the computer vision community. To build a robust SL recognition system, we need a considerable amount of data which is lacking particularly in Indian sign language (ISL). In this paper, we introduce a large-scale isolated ISL dataset and a novel SL recognition model based on skeleton graph structure. The dataset covers 2002 daily used common words in the deaf community recorded by 20 (10 male and 10 female) deaf adult signers (contains 40033 videos). We propose a SL recognition model namely Hierarchical Windowed Graph Attention Network (HWGAT) by utilizing the human upper body skeleton graph. The HWGAT tries to capture distinctive motions by giving attention to different body parts induced by the human skeleton graph. The utility of the proposed dataset and the usefulness of our model are evaluated through extensive experiments. We pre-trained the proposed model on the presented dataset and fine-tuned it across different sign language datasets further boosting the performance of 1.10, 0.46, 0.78, and 6.84 percentage points on INCLUDE, LSA64, AUTSL and WLASL respectively compared to the existing state-of-the-art keypoints-based models.

Supervised learning methods have been found to exhibit inductive biases favoring simpler features. When such features are spuriously correlated with the label, this can result in suboptimal performance on minority subgroups. Despite the growing popularity of methods which learn from unlabeled data, the extent to which these representations rely on spurious features for prediction is unclear. In this work, we explore the impact of spurious features on Self-Supervised Learning (SSL) for visual representation learning. We first empirically show that commonly used augmentations in SSL can cause undesired invariances in the image space, and illustrate this with a simple example. We further show that classical approaches in combating spurious correlations, such as dataset re-sampling during SSL, do not consistently lead to invariant representations. Motivated by these findings, we propose LateTVG to remove spurious information from these representations during pre-training, by regularizing later layers of the encoder via pruning. We find that our method produces representations which outperform the baselines on several benchmarks, without the need for group or label information during SSL.

Depth completion from RGB images and sparse Time-of-Flight (ToF) measurements is an important problem in computer vision and robotics. While traditional methods for depth completion have relied on stereo vision or structured light techniques, recent advances in deep learning have enabled more accurate and efficient completion of depth maps from RGB images and sparse ToF measurements. To evaluate the performance of different depth completion methods, we organized an RGB+sparse ToF depth completion competition. The competition aimed to encourage research in this area by providing a standardized dataset and evaluation metrics to compare the accuracy of different approaches. In this report, we present the results of the competition and analyze the strengths and weaknesses of the top-performing methods. We also discuss the implications of our findings for future research in RGB+sparse ToF depth completion. We hope that this competition and report will help to advance the state-of-the-art in this important area of research. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2023., Comment: arXiv admin note: substantial text overlap with arXiv:2209.07057

Meaningful uncertainty quantification in computer vision requires reasoning about semantic information -- say, the hair color of the person in a photo or the location of a car on the street. To this end, recent breakthroughs in generative modeling allow us to represent semantic information in disentangled latent spaces, but providing uncertainties on the semantic latent variables has remained challenging. In this work, we provide principled uncertainty intervals that are guaranteed to contain the true semantic factors for any underlying generative model. The method does the following: (1) it uses quantile regression to output a heuristic uncertainty interval for each element in the latent space (2) calibrates these uncertainties such that they contain the true value of the latent for a new, unseen input. The endpoints of these calibrated intervals can then be propagated through the generator to produce interpretable uncertainty visualizations for each semantic factor. This technique reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in inverse problems like image super-resolution and image completion., Comment: Accepted to NeurIPS 2022. Project page: https://swamiviv.github.io/semantic_uncertainty_intervals/

We investigate the efficacy of visual prompting to adapt large-scale models in vision. Following the recent approach from prompt tuning and adversarial reprogramming, we learn a single image perturbation such that a frozen model prompted with this perturbation performs a new task. Through comprehensive experiments, we demonstrate that visual prompting is particularly effective for CLIP and robust to distribution shift, achieving performance competitive with standard linear probes. We further analyze properties of the downstream dataset, prompt design, and output transformation in regard to adaptation performance. The surprising effectiveness of visual prompting provides a new perspective on adapting pre-trained models in vision. Code is available at http://hjbahng.github.io/visual_prompting ., Comment: 16 pages, 10 figures

This paper presents a novel multi-fake evolutionary generative adversarial network(MFEGAN) for handling imbalance hyperspectral image classification. It is an end-to-end approach in which different generative objective losses are considered in the generator network to improve the classification performance of the discriminator network. Thus, the same discriminator network has been used as a standard classifier by embedding the classifier network on top of the discriminating function. The effectiveness of the proposed method has been validated through two hyperspectral spatial-spectral data sets. The same generative and discriminator architectures have been utilized with two different GAN objectives for a fair performance comparison with the proposed method. It is observed from the experimental validations that the proposed method outperforms the state-of-the-art methods with better classification performance.

The emergence of Internet of Things (IoT) brings about new security challenges at the intersection of cyber and physical spaces. One prime example is the vulnerability of Face Recognition (FR) based access control in IoT systems. While previous research has shown that Deep Neural Network(DNN)-based FR systems (FRS) are potentially susceptible to imperceptible impersonation attacks, the potency of such attacks in a wide set of scenarios has not been thoroughly investigated. In this paper, we present the first systematic, wide-ranging measurement study of the exploitability of DNN-based FR systems using a large scale dataset. We find that arbitrary impersonation attacks, wherein an arbitrary attacker impersonates an arbitrary target, are hard if imperceptibility is an auxiliary goal. Specifically, we show that factors such as skin color, gender, and age, impact the ability to carry out an attack on a specific target victim, to different extents. We also study the feasibility of constructing universal attacks that are robust to different poses or views of the attacker's face. Our results show that finding a universal perturbation is a much harder problem from the attacker's perspective. Finally, we find that the perturbed images do not generalize well across different DNN models. This suggests security countermeasures that can dramatically reduce the exploitability of DNN-based FR systems., Comment: accepted and appears in ICCCN 2020

There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs) in machine vision; most of these perturbation-based attacks target object classifiers. Inspired by the observation that humans are able to recognize objects that appear out of place in a scene or along with other unlikely objects, we augment the DNN with a system that learns context consistency rules during training and checks for the violations of the same during testing. Our approach builds a set of auto-encoders, one for each object class, appropriately trained so as to output a discrepancy between the input and output if an added adversarial perturbation violates context consistency rules. Experiments on PASCAL VOC and MS COCO show that our method effectively detects various adversarial attacks and achieves high ROC-AUC (over 0.95 in most cases); this corresponds to over 20% improvement over a state-of-the-art context-agnostic method., Comment: The paper is accepted by ECCV 2020

Single image depth estimation is a challenging problem. The current state-of-the-art method formulates the problem as that of ordinal regression. However, the formulation is not fully differentiable and depth maps are not generated in an end-to-end fashion. The method uses a na\"ive threshold strategy to determine per-pixel depth labels, which results in significant discretization errors. For the first time, we formulate a fully differentiable ordinal regression and train the network in end-to-end fashion. This enables us to include boundary and smoothness constraints in the optimization function, leading to smooth and edge-consistent depth maps. A novel per-pixel confidence map computation for depth refinement is also proposed. Extensive evaluation of the proposed model on challenging benchmarks reveals its superiority over recent state-of-the-art methods, both quantitatively and qualitatively. Additionally, we demonstrate practical utility of the proposed method for single camera bokeh solution using in-house dataset of challenging real-life images., Comment: Accepted in IEEE ICIP 2020

Single stage deep learning algorithm for 2D object detection was made popular by Single Shot MultiBox Detector (SSD) and it was heavily adopted in several embedded applications. PointPillars is a state of the art 3D object detection algorithm that uses a Single Shot Detector adapted for 3D object detection. The main downside of PointPillars is that it has a two stage approach with learned input representation based on fully connected layers followed by the Single Shot Detector for 3D detection. In this paper we present Single Shot 3D Object Detection (SS3D) - a single stage 3D object detection algorithm which combines straight forward, statistically computed input representation and a Single Shot Detector (based on PointPillars). Computing the input representation is straight forward, does not involve learning and does not have much computational cost. We also extend our method to stereo input and show that, aided by additional semantic segmentation input; our method produces similar accuracy as state of the art stereo based detectors. Achieving the accuracy of two stage detectors using a single stage approach is important as single stage approaches are simpler to implement in embedded, real-time applications. With LiDAR as well as stereo input, our method outperforms PointPillars. When using LiDAR input, our input representation is able to improve the AP3D of Cars objects in the moderate category from 74.99 to 76.84. When using stereo input, our input representation is able to improve the AP3D of Cars objects in the moderate category from 38.13 to 45.13. Our results are also better than other popular 3D object detectors such as AVOD and F-PointNet.

Recent deep learning based approaches have outperformed classical stereo matching methods. However, current deep learning based end-to-end stereo matching methods adopt a generic encoder-decoder style network with skip connections. To limit computational requirement, many networks perform excessive down sampling, which results in significant loss of useful low-level information. Additionally, many network designs do not exploit the rich multi-scale contextual information. In this work, we address these aforementioned problems by carefully designing the network architecture to preserve required spatial information throughout the network, while at the same time achieve large effective receptive field to extract multiscale contextual information. For the first time, we create a synthetic disparity dataset reflecting real life images captured using a smartphone; this enables us to obtain state-of-the-art results on common real life images. The proposed model DISCO is pre-trained on the synthetic Scene Flow dataset and evaluated on popular benchmarks and our in-house dataset of challenging real life images. The proposed model outperforms existing state-of-the-art methods in terms of quality as well as quantitative metrics., Comment: This work was completed in October 2018 and is accepted in IEEE International Conference on Multimedia & Expo (ICME) 2019

The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the "truth" under the influence of their varying skill-levels and biases. Blindly treating these noisy labels as the ground truth limits the accuracy of learning algorithms in the presence of strong disagreement. This problem is critical for applications in domains such as medical imaging where both the annotation cost and inter-observer variability are high. In this work, we present a method for simultaneously learning the individual annotator model and the underlying true label distribution, using only noisy observations. Each annotator is modeled by a confusion matrix that is jointly estimated along with the classifier predictions. We propose to add a regularization term to the loss function that encourages convergence to the true annotator confusion matrix. We provide a theoretical argument as to how the regularization is essential to our approach both for the case of single annotator and multiple annotators. Despite the simplicity of the idea, experiments on image classification tasks with both simulated and real labels show that our method either outperforms or performs on par with the state-of-the-art methods and is capable of estimating the skills of annotators even with a single label available per image., Comment: CVPR 2019, code snippets included

Recent research has demonstrated the brittleness of machine learning systems to adversarial perturbations. However, the studies have been mostly limited to perturbations on images and more generally, classification that does not deal with temporally varying inputs. In this paper we ask "Are adversarial perturbations possible in real-time video classification systems and if so, what properties must they satisfy?" Such systems find application in surveillance applications, smart vehicles, and smart elderly care and thus, misclassification could be particularly harmful (e.g., a mishap at an elderly care facility may be missed). We show that accounting for temporal structure is key to generating adversarial examples in such systems. We exploit recent advances in generative adversarial network (GAN) architectures to account for temporal correlations and generate adversarial samples that can cause misclassification rates of over 80% for targeted activities. More importantly, the samples also leave other activities largely unaffected making them extremely stealthy. Finally, we also surprisingly find that in many scenarios, the same perturbation can be applied to every frame in a video clip that makes the adversary's ability to achieve misclassification relatively easy.

In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. A typical pipeline for face verification includes training a deep network for subject classification with softmax loss, using the penultimate layer output as the feature descriptor, and generating a cosine similarity score given a pair of face images or videos. The softmax loss function does not optimize the features to have higher similarity score for positive pairs and lower similarity score for negative pairs, which leads to a performance gap. In this paper, we propose a new loss function, called Crystal Loss, that restricts the features to lie on a hypersphere of a fixed radius. The loss can be easily implemented using existing deep learning frameworks. We show that integrating this simple step in the training pipeline significantly improves the performance of face verification and recognition systems. We achieve state-of-the-art performance for face verification and recognition on challenging LFW, IJB-A, IJB-B and IJB-C datasets over a large range of false alarm rates (10-1 to 10-7)., Comment: Previously portions of this work appeared in arXiv:1703.09507, which was a conference version. This version is an extended journal version of it

Single image haze removal is a very challenging and ill-posed problem. The existing haze removal methods in literature, including the recently introduced deep learning methods, model the problem of haze removal as that of estimating intermediate parameters, viz., scene transmission map and atmospheric light. These are used to compute the haze-free image from the hazy input image. Such an approach only focuses on accurate estimation of intermediate parameters, while the aesthetic quality of the haze-free image is unaccounted for in the optimization framework. Thus, errors in the estimation of intermediate parameters often lead to generation of inferior quality haze-free images. In this paper, we present CANDY (Conditional Adversarial Networks based Dehazing of hazY images), a fully end-to-end model which directly generates a clean haze-free image from a hazy input image. CANDY also incorporates the visual quality of haze-free image into the optimization function; thus, generating a superior quality haze-free image. To the best of our knowledge, this is the first work in literature to propose a fully end-to-end model for single image haze removal. Also, this is the first work to explore the newly introduced concept of generative adversarial networks for the problem of single image haze removal. The proposed model CANDY was trained on a synthetically created haze image dataset, while evaluation was performed on challenging synthetic as well as real haze image datasets. The extensive evaluation and comparison results of CANDY reveal that it significantly outperforms existing state-of-the-art haze removal methods in literature, both quantitatively as well as qualitatively., Comment: 10 pages, 7 figures

Image orientation detection requires high-level scene understanding. Humans use object recognition and contextual scene information to correctly orient images. In literature, the problem of image orientation detection is mostly confronted by using low-level vision features, while some approaches incorporate few easily detectable semantic cues to gain minor improvements. The vast amount of semantic content in images makes orientation detection challenging, and therefore there is a large semantic gap between existing methods and human behavior. Also, existing methods in literature report highly discrepant detection rates, which is mainly due to large differences in datasets and limited variety of test images used for evaluation. In this work, for the first time, we leverage the power of deep learning and adapt pre-trained convolutional neural networks using largest training dataset to-date for the image orientation detection task. An extensive evaluation of our model on different public datasets shows that it remarkably generalizes to correctly orient a large set of unconstrained images; it also significantly outperforms the state-of-the-art and achieves accuracy very close to that of humans.

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe for tasks where acquiring hand labeled data is extremely hard and tedious. In this work, we focus on adapting the representations learned by segmentation networks across synthetic and real domains. Contrary to previous approaches that use a simple adversarial objective or superpixel information to aid the process, we propose an approach based on Generative Adversarial Networks (GANs) that brings the embeddings closer in the learned feature space. To showcase the generality and scalability of our approach, we show that we can achieve state of the art results on two challenging scenarios of synthetic to real domain adaptation. Additional exploratory experiments show that our approach: (1) generalizes to unseen domains and (2) results in improved alignment of source and target distributions., Comment: Accepted as spotlight talk at CVPR 2018. Code available here: https://github.com/swamiviv/LSD-seg

Adversarial training has been shown to regularize deep neural networks in addition to increasing their robustness to adversarial examples. However, its impact on very deep state of the art networks has not been fully investigated. In this paper, we present an efficient approach to perform adversarial training by perturbing intermediate layer activations and study the use of such perturbations as a regularizer during training. We use these perturbations to train very deep models such as ResNets and show improvement in performance both on adversarial and original test data. Our experiments highlight the benefits of perturbing intermediate layer activations compared to perturbing only the inputs. The results on CIFAR-10 and CIFAR-100 datasets show the merits of the proposed adversarial training approach. Additional results on WideResNets show that our approach provides significant improvement in classification accuracy for a given base model, outperforming dropout and other base models of larger size., Comment: Published at the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18). Official link: https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16634

Domain Adaptation is an actively researched problem in Computer Vision. In this work, we propose an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space. We accomplish this by inducing a symbiotic relationship between the learned embedding and a generative adversarial network. This is in contrast to methods which use the adversarial framework for realistic data generation and retraining deep models with such data. We demonstrate the strength and generality of our approach by performing experiments on three different tasks with varying levels of difficulty: (1) Digit classification (MNIST, SVHN and USPS datasets) (2) Object recognition using OFFICE dataset and (3) Domain adaptation from synthetic to real data. Our method achieves state-of-the art performance in most experimental settings and by far the only GAN-based method that has been shown to work well across different datasets such as OFFICE and DIGITS., Comment: Accepted as spotlight talk at CVPR 2018. Code available here: https://github.com/yogeshbalaji/Generate_To_Adapt

Convolutional Neural Networks have been a subject of great importance over the past decade and great strides have been made in their utility for producing state of the art performance in many computer vision problems. However, the behavior of deep networks is yet to be fully understood and is still an active area of research. In this work, we present an intriguing behavior: pre-trained CNNs can be made to improve their predictions by structurally perturbing the input. We observe that these perturbations - referred as Guided Perturbations - enable a trained network to improve its prediction performance without any learning or change in network weights. We perform various ablative experiments to understand how these perturbations affect the local context and feature representations. Furthermore, we demonstrate that this idea can improve performance of several existing approaches on semantic segmentation and scene labeling tasks on the PASCAL VOC dataset and supervised classification tasks on MNIST and CIFAR10 datasets., Comment: Accepted to ICCV 2017

Face recognition algorithms based on deep convolutional neural networks (DCNNs) have made progress on the task of recognizing faces in unconstrained viewing conditions. These networks operate with compact feature-based face representations derived from learning a very large number of face images. While the learned features produced by DCNNs can be highly robust to changes in viewpoint, illumination, and appearance, little is known about the nature of the face code that emerges at the top level of such networks. We analyzed the DCNN features produced by two face recognition algorithms. In the first set of experiments we used the top-level features from the DCNNs as input into linear classifiers aimed at predicting metadata about the images. The results show that the DCNN features contain surprisingly accurate information about the yaw and pitch of a face, and about whether the face came from a still image or a video frame. In the second set of experiments, we measured the extent to which individual DCNN features operated in a view-dependent or view-invariant manner. We found that view-dependent coding was a characteristic of the identities rather than the DCNN features - with some identities coded consistently in a view-dependent way and others in a view-independent way. In our third analysis, we visualized the DCNN feature space for over 24,000 images of 500 identities. Images in the center of the space were uniformly of low quality (e.g., extreme views, face occlusion, low resolution). Image quality increased monotonically as a function of distance from the origin. This result suggests that image quality information is available in the DCNN features, such that consistently average feature values reflect coding failures that reliably indicate poor or unusable images. Combined, the results offer insight into the coding mechanisms that support robust representation of faces in DCNNs., Comment: Submitted to Face and Gesture Conference, 2017

We present a multi-purpose algorithm for simultaneous face detection, face alignment, pose estimation, gender recognition, smile detection, age estimation and face recognition using a single deep convolutional neural network (CNN). The proposed method employs a multi-task learning framework that regularizes the shared parameters of CNN and builds a synergy among different domains and tasks. Extensive experiments show that the network has a better understanding of face and achieves state-of-the-art result for most of these tasks.

Over the last five years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems. This has been made possible due to the availability of large annotated datasets, a better understanding of the non-linear mapping between input images and class labels as well as the affordability of GPUs. In this paper, we present the design details of a deep learning system for unconstrained face recognition, including modules for face detection, association, alignment and face verification. The quantitative performance evaluation is conducted using the IARPA Janus Benchmark A (IJB-A), the JANUS Challenge Set 2 (JANUS CS2), and the LFW dataset. The IJB-A dataset includes real-world unconstrained faces of 500 subjects with significant pose and illumination variations which are much harder than the Labeled Faces in the Wild (LFW) and Youtube Face (YTF) datasets. JANUS CS2 is the extended version of IJB-A which contains not only all the images/frames of IJB-A but also includes the original videos for evaluating the video-based face verification system. Some open issues regarding DCNNs for face verification problems are then discussed., Comment: accepted by IJCV

Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative embedding learned using triplet probability constraints to solve the unconstrained face verification problem. Aside from yielding performance improvements, this embedding provides significant advantages in terms of memory and for post-processing operations like subject specific clustering. Experiments on the challenging IJB-A dataset show that the proposed algorithm performs comparably or better than the state of the art methods in verification and identification metrics, while requiring much less training data and training time. The superior performance of the proposed method on the CFP dataset shows that the representation learned by our deep CNN is robust to extreme pose variation. Furthermore, we demonstrate the robustness of the deep features to challenges including age, pose, blur and clutter by performing simple clustering experiments on both IJB-A and LFW datasets., Comment: Oral Paper in BTAS 2016; NVIDIA Best paper Award (http://ieee-biometrics.org/btas2016/awards.html)

In this work, we present an unconstrained face verification algorithm and evaluate it on the recently released IJB-A dataset that aims to push the boundaries of face verification methods. The proposed algorithm couples a deep CNN-based approach with a low-dimensional discriminative embedding learnt using triplet similarity constraints in a large margin fashion. Aside from yielding performance improvement, this embedding provides significant advantages in terms of memory and post-processing operations like hashing and visualization. Experiments on the IJB-A dataset show that the proposed algorithm outperforms state of the art methods in verification and identification metrics, while requiring less training time.

Over many decades, researchers working in object recognition have longed for an end-to-end automated system that will simply accept 2D or 3D image or videos as inputs and output the labels of objects in the input data. Computer vision methods that use representations derived based on geometric, radiometric and neural considerations and statistical and structural matchers and artificial neural network-based methods where a multi-layer network learns the mapping from inputs to class labels have provided competing approaches for image recognition problems. Over the last four years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements on object detection/recognition challenge problems. This has been made possible due to the availability of large annotated data, a better understanding of the non-linear mapping between image and class labels as well as the affordability of GPUs. In this paper, we present a brief history of developments in computer vision and artificial neural networks over the last forty years for the problem of image-based recognition. We then present the design details of a deep learning system for end-to-end unconstrained face verification/recognition. Some open issues regarding DCNNs for object recognition problems are then discussed. We caution the readers that the views expressed in this paper are from the authors and authors only!, Comment: 7 pages