arXiv subjects

Chetan Arora

Publications and source records attributed to Chetan Arora.

At least 109 records · Page 6Linked to original sources

arXiv2022

Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining

Rich temporal information and variations in viewpoints make video data an attractive choice for learning image representations using unsupervised contrastive learning (UCL) techniques. State-of-the-art (SOTA) contrastive learning techniques consider frames within a video as positives in the embedding space, whereas the frames from other videos are considered negatives. We observe that unlike multiple views of an object in natural scene videos, an Ultrasound (US) video captures different 2D slices of an organ. Hence, there is almost no similarity between the temporally distant frames of even the same US video. In this paper we propose to instead utilize such frames as hard negatives. We advocate mining both intra-video and cross-video negatives in a hardness-sensitive negative mining curriculum in a UCL framework to learn rich image representations. We deploy our framework to learn the representations of Gallbladder (GB) malignancy from US videos. We also construct the first large-scale US video dataset containing 64 videos and 15,800 frames for learning GB representations. We show that the standard ResNet50 backbone trained with our framework improves the accuracy of models pretrained with SOTA UCL techniques as well as supervised pretrained models on ImageNet for the GB malignancy detection task by 2-6%. We further validate the generalizability of our method on a publicly available lung US image dataset of COVID-19 pathologies and show an improvement of 1.5% compared to SOTA. Source code, dataset, and models are available at https://gbc-iitd.github.io/usucl.

eess.IV↗

arXiv2022

My View is the Best View: Procedure Learning from Egocentric Videos

Procedure learning involves identifying the key-steps and determining their logical order to perform a task. Existing approaches commonly use third-person videos for learning the procedure, making the manipulated object small in appearance and often occluded by the actor, leading to significant errors. In contrast, we observe that videos obtained from first-person (egocentric) wearable cameras provide an unobstructed and clear view of the action. However, procedure learning from egocentric videos is challenging because (a) the camera view undergoes extreme changes due to the wearer's head motion, and (b) the presence of unrelated frames due to the unconstrained nature of the videos. Due to this, current state-of-the-art methods' assumptions that the actions occur at approximately the same time and are of the same duration, do not hold. Instead, we propose to use the signal provided by the temporal correspondences between key-steps across videos. To this end, we present a novel self-supervised Correspond and Cut (CnC) framework for procedure learning. CnC identifies and utilizes the temporal correspondences between the key-steps across multiple videos to learn the procedure. Our experiments show that CnC outperforms the state-of-the-art on the benchmark ProceL and CrossTask datasets by 5.2% and 6.3%, respectively. Furthermore, for procedure learning using egocentric videos, we propose the EgoProceL dataset consisting of 62 hours of videos captured by 130 subjects performing 16 tasks. The source code and the dataset are available on the project page https://sid2697.github.io/egoprocel/.

cs.CV↗

arXiv2022

Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion

Attention-based models such as transformers have shown outstanding performance on dense prediction tasks, such as semantic segmentation, owing to their capability of capturing long-range dependency in an image. However, the benefit of transformers for monocular depth prediction has seldom been explored so far. This paper benchmarks various transformer-based models for the depth estimation task on an indoor NYUV2 dataset and an outdoor KITTI dataset. We propose a novel attention-based architecture, Depthformer for monocular depth estimation that uses multi-head self-attention to produce the multiscale feature maps, which are effectively combined by our proposed decoder network. We also propose a Transbins module that divides the depth range into bins whose center value is estimated adaptively per image. The final depth estimated is a linear combination of bin centers for each pixel. Transbins module takes advantage of the global receptive field using the transformer module in the encoding stage. Experimental results on NYUV2 and KITTI depth estimation benchmark demonstrate that our proposed method improves the state-of-the-art by 3.3%, and 3.3% respectively in terms of Root Mean Squared Error (RMSE). Code is available at https://github.com/ashutosh1807/Depthformer.git.

cs.CV↗

arXiv2022

TAPHSIR: Towards AnaPHoric Ambiguity Detection and ReSolution In Requirements

We introduce TAPHSIR, a tool for anaphoric ambiguity detection and anaphora resolution in requirements. TAPHSIR facilities reviewing the use of pronouns in a requirements specification and revising those pronouns that can lead to misunderstandings during the development process. To this end, TAPHSIR detects the requirements which have potential anaphoric ambiguity and further attempts interpreting anaphora occurrences automatically. TAPHSIR employs a hybrid solution composed of an ambiguity detection solution based on machine learning and an anaphora resolution solution based on a variant of the BERT language model. Given a requirements specification, TAPHSIR decides for each pronoun occurrence in the specification whether the pronoun is ambiguous or unambiguous, and further provides an automatic interpretation for the pronoun. The output generated by TAPHSIR can be easily reviewed and validated by requirements engineers. TAPHSIR is publicly available on Zenodo (DOI: 10.5281/zenodo.5902117).

cs.SE↗

arXiv2022

COREQQA -- A COmpliance REQuirements Understanding using Question Answering Tool

We introduce COREQQA, a tool for assisting requirements engineers in acquiring a better understanding of compliance requirements by means of automated Question Answering. Extracting compliance-related requirements by manually navigating through a legal document is both time-consuming and error-prone. COREQQA enables requirements engineers to pose questions in natural language about a compliance-related topic given some legal document, e.g., asking about data breach. The tool then automatically navigates through the legal document and returns to the requirements engineer a list of text passages containing the possible answers to the input question. For better readability, the tool also highlights the likely answers in these passages. The engineer can then use this output for specifying compliance requirements. COREQQA is developed using advanced large-scale language models from BERT's family. COREQQA has been evaluated on four legal documents. The results of this evaluation are briefly presented in the paper. The tool is publicly available on Zenodo (DOI: 10.5281/zenodo.6653514).

cs.SE↗

arXiv2022

Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning

We explore the potential of CNN-based models for gallbladder cancer (GBC) detection from ultrasound (USG) images as no prior study is known. USG is the most common diagnostic modality for GB diseases due to its low cost and accessibility. However, USG images are challenging to analyze due to low image quality, noise, and varying viewpoints due to the handheld nature of the sensor. Our exhaustive study of state-of-the-art (SOTA) image classification techniques for the problem reveals that they often fail to learn the salient GB region due to the presence of shadows in the USG images. SOTA object detection techniques also achieve low accuracy because of spurious textures due to noise or adjacent organs. We propose GBCNet to tackle the challenges in our problem. GBCNet first extracts the regions of interest (ROIs) by detecting the GB (and not the cancer), and then uses a new multi-scale, second-order pooling architecture specializing in classifying GBC. To effectively handle spurious textures, we propose a curriculum inspired by human visual acuity, which reduces the texture biases in GBCNet. Experimental results demonstrate that GBCNet significantly outperforms SOTA CNN models, as well as the expert radiologists. Our technical innovations are generic to other USG image analysis tasks as well. Hence, as a validation, we also show the efficacy of GBCNet in detecting breast cancer from USG images. Project page with source code, trained models, and data is available at https://gbc-iitd.github.io/gbcnet

cs.CV↗

arXiv2022

A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration

Deep Neural Networks ( DNN s) are known to make overconfident mistakes, which makes their use problematic in safety-critical applications. State-of-the-art ( SOTA ) calibration techniques improve on the confidence of predicted labels alone and leave the confidence of non-max classes (e.g. top-2, top-5) uncalibrated. Such calibration is not suitable for label refinement using post-processing. Further, most SOTA techniques learn a few hyper-parameters post-hoc, leaving out the scope for image, or pixel specific calibration. This makes them unsuitable for calibration under domain shift, or for dense prediction tasks like semantic segmentation. In this paper, we argue for intervening at the train time itself, so as to directly produce calibrated DNN models. We propose a novel auxiliary loss function: Multi-class Difference in Confidence and Accuracy ( MDCA ), to achieve the same MDCA can be used in conjunction with other application/task-specific loss functions. We show that training with MDCA leads to better-calibrated models in terms of Expected Calibration Error ( ECE ), and Static Calibration Error ( SCE ) on image classification, and segmentation tasks. We report ECE ( SCE ) score of 0.72 (1.60) on the CIFAR 100 dataset, in comparison to 1.90 (1.71) by the SOTA. Under domain shift, a ResNet-18 model trained on PACS dataset using MDCA gives an average ECE ( SCE ) score of 19.7 (9.7) across all domains, compared to 24.2 (11.8) by the SOTA. For the segmentation task, we report a 2X reduction in calibration error on PASCAL - VOC dataset in comparison to Focal Loss. Finally, MDCA training improves calibration even on imbalanced data, and for natural language classification tasks. We have released the code here: code is available at https://github.com/mdca-loss

cs.CV↗

arXiv2022

Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey

A Machine-Critical Application is a system that is fundamentally necessary to the success of specific and sensitive operations such as search and recovery, rescue, military, and emergency management actions. Recent advances in Machine Learning, Natural Language Processing, voice recognition, and speech processing technologies have naturally allowed the development and deployment of speech-based conversational interfaces to interact with various machine-critical applications. While these conversational interfaces have allowed users to give voice commands to carry out strategic and critical activities, their robustness to adversarial attacks remains uncertain and unclear. Indeed, Adversarial Artificial Intelligence (AI) which refers to a set of techniques that attempt to fool machine learning models with deceptive data, is a growing threat in the AI and machine learning research community, in particular for machine-critical applications. The most common reason of adversarial attacks is to cause a malfunction in a machine learning model. An adversarial attack might entail presenting a model with inaccurate or fabricated samples as it's training data, or introducing maliciously designed data to deceive an already trained model. While focusing on speech recognition for machine-critical applications, in this paper, we first review existing speech recognition techniques, then, we investigate the effectiveness of adversarial attacks and defenses against these systems, before outlining research challenges, defense recommendations, and future work. This paper is expected to serve researchers and practitioners as a reference to help them in understanding the challenges, position themselves and, ultimately, help them to improve existing models of speech recognition for mission-critical applications. Keywords: Mission-Critical Applications, Adversarial AI, Speech Recognition Systems.

cs.SD↗

arXiv2021

Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection

Few-shot object detection (FSOD) localizes and classifies objects in an image given only a few data samples. Recent trends in FSOD research show the adoption of metric and meta-learning techniques, which are prone to catastrophic forgetting and class confusion. To overcome these pitfalls in metric learning based FSOD techniques, we introduce Attention Guided Cosine Margin (AGCM) that facilitates the creation of tighter and well separated class-specific feature clusters in the classification head of the object detector. Our novel Attentive Proposal Fusion (APF) module minimizes catastrophic forgetting by reducing the intra-class variance among co-occurring classes. At the same time, the proposed Cosine Margin Cross-Entropy loss increases the angular margin between confusing classes to overcome the challenge of class confusion between already learned (base) and newly added (novel) classes. We conduct our experiments on the challenging India Driving Dataset (IDD), which presents a real-world class-imbalanced setting alongside popular FSOD benchmark PASCAL-VOC. Our method outperforms State-of-the-Art (SoTA) approaches by up to 6.4 mAP points on the IDD-OS and up to 2.0 mAP points on the IDD-10 splits for the 10-shot setting. On the PASCAL-VOC dataset, we outperform existing SoTA approaches by up to 4.9 mAP points.

cs.CV↗

arXiv2021

Multi-Domain Incremental Learning for Semantic Segmentation

Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation datasets demonstrates that existing segmentation frameworks fail at incrementally learning on a series of visually disparate geographical domains. When learning a new domain, the model catastrophically forgets previously learned knowledge. In this work, we pose the problem of multi-domain incremental learning for semantic segmentation. Given a model trained on a particular geographical domain, the goal is to (i) incrementally learn a new geographical domain, (ii) while retaining performance on the old domain, (iii) given that the previous domain's dataset is not accessible. We propose a dynamic architecture that assigns universally shared, domain-invariant parameters to capture homogeneous semantic features present in all domains, while dedicated domain-specific parameters learn the statistics of each domain. Our novel optimization strategy helps achieve a good balance between retention of old knowledge (stability) and acquiring new knowledge (plasticity). We demonstrate the effectiveness of our proposed solution on domain incremental settings pertaining to real-world driving scenes from roads of Germany (Cityscapes), the United States (BDD100k), and India (IDD).

cs.CV↗

arXiv2021

Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias

Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. However, co-occurrence bias in the training dataset may hamper a DNN model's generalizability to unseen scenarios in the real world. For example, in COCO, many object categories have a much higher co-occurrence with men compared to women, which can bias a DNN's prediction in favor of men. Recent works have focused on task-specific training strategies to handle bias in such scenarios, but fixing the available data is often ignored. In this paper, we propose a novel and more generic solution to address the contextual bias in the datasets by selecting a subset of the samples, which is fair in terms of the co-occurrence with various classes for a protected attribute. We introduce a data repair algorithm using the coefficient of variation, which can curate fair and contextually balanced data for a protected class(es). This helps in training a fair model irrespective of the task, architecture or training methodology. Our proposed solution is simple, effective, and can even be used in an active learning setting where the data labels are not present or being generated incrementally. We demonstrate the effectiveness of our algorithm for the task of object detection and multi-label image classification across different datasets. Through a series of experiments, we validate that curating contextually fair data helps make model predictions fair by balancing the true positive rate for the protected class across groups without compromising on the model's overall performance.

cs.CV↗

arXiv2021

Internet of Things in Space: A Review of Opportunities and Challenges from Satellite-Aided Computing to Digitally-Enhanced Space Living

Recent scientific and technological advancements driven by the Internet of Things (IoT), Machine Learning (ML) and Artificial Intelligence (AI), distributed computing and data communication technologies have opened up a vast range of opportunities in many scientific fields - spanning from fast, reliable and efficient data communication to large-scale cloud/edge computing and intelligent big data analytics. Technological innovations and developments in these areas have also enabled many opportunities in the space industry. The successful Mars landing of NASA's Perseverance rover on February 18, 2021 represents another giant leap for mankind in space exploration. Emerging research and developments of connectivity and computing technologies in IoT for space/non-terrestrial environments is expected to yield significant benefits in the near future. This survey paper presents a broad overview of the area and provides a look-ahead of the opportunities made possible by IoT and space-based technologies. We first survey the current developments of IoT and space industry, and identify key challenges and opportunities in these areas. We then review the state-of-the-art and discuss future opportunities for IoT developments, deployment and integration to support future endeavours in space exploration.

cs.DC↗

arXiv2021

Efficient and Generic Interactive Segmentation Framework to Correct Mispredictions during Clinical Evaluation of Medical Images

Semantic segmentation of medical images is an essential first step in computer-aided diagnosis systems for many applications. However, given many disparate imaging modalities and inherent variations in the patient data, it is difficult to consistently achieve high accuracy using modern deep neural networks (DNNs). This has led researchers to propose interactive image segmentation techniques where a medical expert can interactively correct the output of a DNN to the desired accuracy. However, these techniques often need separate training data with the associated human interactions, and do not generalize to various diseases, and types of medical images. In this paper, we suggest a novel conditional inference technique for DNNs which takes the intervention by a medical expert as test time constraints and performs inference conditioned upon these constraints. Our technique is generic can be used for medical images from any modality. Unlike other methods, our approach can correct multiple structures simultaneously and add structures missed at initial segmentation. We report an improvement of 13.3, 12.5, 17.8, 10.2, and 12.4 times in user annotation time than full human annotation for the nucleus, multiple cells, liver and tumor, organ, and brain segmentation respectively. We report a time saving of 2.8, 3.0, 1.9, 4.4, and 8.6 fold compared to other interactive segmentation techniques. Our method can be useful to clinicians for diagnosis and post-surgical follow-up with minimal intervention from the medical expert. The source-code and the detailed results are available here [1].

cs.CV↗

arXiv2020

Contextual Diversity for Active Learning

Requirement of large annotated datasets restrict the use of deep convolutional neural networks (CNNs) for many practical applications. The problem can be mitigated by using active learning (AL) techniques which, under a given annotation budget, allow to select a subset of data that yields maximum accuracy upon fine tuning. State of the art AL approaches typically rely on measures of visual diversity or prediction uncertainty, which are unable to effectively capture the variations in spatial context. On the other hand, modern CNN architectures make heavy use of spatial context for achieving highly accurate predictions. Since the context is difficult to evaluate in the absence of ground-truth labels, we introduce the notion of contextual diversity that captures the confusion associated with spatially co-occurring classes. Contextual Diversity (CD) hinges on a crucial observation that the probability vector predicted by a CNN for a region of interest typically contains information from a larger receptive field. Exploiting this observation, we use the proposed CD measure within two AL frameworks: (1) a core-set based strategy and (2) a reinforcement learning based policy, for active frame selection. Our extensive empirical evaluation establish state of the art results for active learning on benchmark datasets of Semantic Segmentation, Object Detection and Image Classification. Our ablation studies show clear advantages of using contextual diversity for active learning. The source code and additional results are available at https://github.com/sharat29ag/CDAL.

cs.CV↗

arXiv2020

Dynamic Adaptation of Software-defined Networks for IoT Systems: A Search-based Approach

The concept of Internet of Things (IoT) has led to the development of many complex and critical systems such as smart emergency management systems. IoT-enabled applications typically depend on a communication network for transmitting large volumes of data in unpredictable and changing environments. These networks are prone to congestion when there is a burst in demand, e.g., as an emergency situation is unfolding, and therefore rely on configurable software-defined networks (SDN). In this paper, we propose a dynamic adaptive SDN configuration approach for IoT systems. The approach enables resolving congestion in real time while minimizing network utilization, data transmission delays and adaptation costs. Our approach builds on existing work in dynamic adaptive search-based software engineering (SBSE) to reconfigure an SDN while simultaneously ensuring multiple quality of service criteria. We evaluate our approach on an industrial national emergency management system, which is aimed at detecting disasters and emergencies, and facilitating recovery and rescue operations by providing first responders with a reliable communication infrastructure. Our results indicate that (1) our approach is able to efficiently and effectively adapt an SDN to dynamically resolve congestion, and (2) compared to two baseline data forwarding algorithms that are static and non-adaptive, our approach increases data transmission rate by a factor of at least 3 and decreases data loss by at least 70%.

cs.SE↗

arXiv2020

CovidAID: COVID-19 Detection Using Chest X-Ray

The exponential increase in COVID-19 patients is overwhelming healthcare systems across the world. With limited testing kits, it is impossible for every patient with respiratory illness to be tested using conventional techniques (RT-PCR). The tests also have long turn-around time, and limited sensitivity. Detecting possible COVID-19 infections on Chest X-Ray may help quarantine high risk patients while test results are awaited. X-Ray machines are already available in most healthcare systems, and with most modern X-Ray systems already digitized, there is no transportation time involved for the samples either. In this work we propose the use of chest X-Ray to prioritize the selection of patients for further RT-PCR testing. This may be useful in an inpatient setting where the present systems are struggling to decide whether to keep the patient in the ward along with other patients or isolate them in COVID-19 areas. It would also help in identifying patients with high likelihood of COVID with a false negative RT-PCR who would need repeat testing. Further, we propose the use of modern AI techniques to detect the COVID-19 patients using X-Ray images in an automated manner, particularly in settings where radiologists are not available, and help make the proposed testing technology scalable. We present CovidAID: COVID-19 AI Detector, a novel deep neural network based model to triage patients for appropriate testing. On the publicly available covid-chestxray-dataset [2], our model gives 90.5% accuracy with 100% sensitivity (recall) for the COVID-19 infection. We significantly improve upon the results of Covid-Net [10] on the same dataset.

eess.IV↗

arXiv2019

A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation

Auxiliary information can be exploited in machine learning models using the paradigm of evidence based conditional inference. Multi-modal techniques in Deep Neural Networks (DNNs) can be seen as perturbing the latent feature representation for incorporating evidence from the auxiliary modality. However, they require training a specialized network which can map sparse evidence to a high dimensional latent space vector. Designing such a network, as well as collecting jointly labeled data for training is a non-trivial task. In this paper, we present a novel multi-task learning (MTL) based framework to perform evidence based conditional inference in DNNs which can overcome both these shortcomings. Our framework incorporates evidence as the output of secondary task(s), while modeling the original problem as the primary task of interest. During inference, we employ a novel Bayesian formulation to change the joint latent feature representation so as to maximize the probability of the observed evidence. Since our approach models evidence as prediction from a DNN, this can often be achieved using standard pre-trained backbones for popular tasks, eliminating the need for training altogether. Even when training is required, our MTL architecture ensures the same can be done without any need for jointly labeled data. Exploiting evidence using our framework, we show an improvement of 3.9% over the state-of-the-art, for predicting semantic segmentation given the image tags, and 2.8% for predicting instance segmentation given image captions.

cs.CV↗

arXiv2019

Diversity in Fashion Recommendation using Semantic Parsing

Developing recommendation system for fashion images is challenging due to the inherent ambiguity associated with what criterion a user is looking at. Suggesting multiple images where each output image is similar to the query image on the basis of a different feature or part is one way to mitigate the problem. Existing works for fashion recommendation have used Siamese or Triplet network to learn features between a similar pair and a similar-dissimilar triplet respectively. However, these methods do not provide basic information such as, how two clothing images are similar, or which parts present in the two images make them similar. In this paper, we propose to recommend images by explicitly learning and exploiting part based similarity. We propose a novel approach of learning discriminative features from weakly-supervised data by using visual attention over the parts and a texture encoding network. We show that the learned features surpass the state-of-the-art in retrieval task on DeepFashion dataset. We then use the proposed model to recommend fashion images having an explicit variation with respect to similarity of any of the parts.

cs.CV↗