132 citations · 332 across the 30 of their papers we have counts for
31 papers
Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks
Ankita Raj, Ambar Pal, Chetan Arora
Backdoor attacks embed a hidden functionality into deep neural networks, causing the network to display anomalous behavior when activated by a predetermined pattern in the input Tr…
Use of Metric Learning for the Recognition of Handwritten Digits, and its Application to Increase the Outreach of Voice-based Communication Platforms
Devesh Pant, Dibyendu Talukder, Deepak Kumar +3
Initiation, monitoring, and evaluation of development programmes can involve field-based data collection about project activities. This data collection through digital devices may…
Gall Bladder Cancer Detection from US Images with Only Image Level Labels
Soumen Basu, Ashish Papanai, Mayank Gupta +2
Automated detection of Gallbladder Cancer (GBC) from Ultrasound (US) images is an important problem, which has drawn increased interest from researchers. However, most of these wor…
UTRNet: High-Resolution Urdu Text Recognition In Printed Documents
Abdur Rahman, Arjun Ghosh, Chetan Arora
In this paper, we propose a novel approach to address the challenges of printed Urdu text recognition using high-resolution, multi-scale semantic feature extraction. Our proposed U…
FinderNet: A Data Augmentation Free Canonicalization aided Loop Detection and Closure technique for Point clouds in 6-DOF separation
Sudarshan S Harithas, Gurkirat Singh, Aneesh Chavan +4
We focus on the problem of LiDAR point cloud based loop detection (or Finding) and closure (LDC) in a multi-agent setting. State-of-the-art (SOTA) techniques directly generate lear…
RadFormer: Transformers with Global-Local Attention for Interpretable and Accurate Gallbladder Cancer Detection
Soumen Basu, Mayank Gupta, Pratyaksha Rana +2
We propose a novel deep neural network architecture to learn interpretable representation for medical image analysis. Our architecture generates a global attention for region of in…
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
Ashutosh Agarwal, Chetan Arora
Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single RGB image. For both, the convolutional as well as the recent attention-based models, encoder-decode…
Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift
Sharat Agarwal, Saket Anand, Chetan Arora
In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adapta…
Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining
Soumen Basu, Somanshu Singla, Mayank Gupta +3
Rich temporal information and variations in viewpoints make video data an attractive choice for learning image representations using unsupervised contrastive learning (UCL) techniq…
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion
Ashutosh Agarwal, Chetan Arora
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…
A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions
Ramya S. Hebbalaguppe, Soumya Suvra Goshal, Jatin Prakash +2
Modern deep neural network models are known to erroneously classify out-of-distribution (OOD) test data into one of the in-distribution (ID) training classes with high confidence.…
Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning
Soumen Basu, Mayank Gupta, Pratyaksha Rana +2
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 modal…
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration
Ramya Hebbalaguppe, Jatin Prakash, Neelabh Madan +1
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 tec…
Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey
Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Imran Razzak +4
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 em…
Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection
Ashutosh Agarwal, Anay Majee, Anbumani Subramanian +1
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-lea…
Multi-Domain Incremental Learning for Semantic Segmentation
Prachi Garg, Rohit Saluja, Vineeth N Balasubramanian +3
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 perfo…
Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias
Sharat Agarwal, Sumanyu Muku, Saket Anand +1
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 m…
Efficient and Generic Interactive Segmentation Framework to Correct Mispredictions during Clinical Evaluation of Medical Images
Bhavani Sambaturu, Ashutosh Gupta, C. V. Jawahar +1
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 i…
Contextual Diversity for Active Learning
Sharat Agarwal, Himanshu Arora, Saket Anand +1
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…
CovidAID: COVID-19 Detection Using Chest X-Ray
Arpan Mangal, Surya Kalia, Harish Rajgopal +4
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 il…
Diversity in Fashion Recommendation using Semantic Parsing
Sagar Verma, Sukhad Anand, Chetan Arora +1
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 whe…
Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos
Sagar Verma, Pravin Nagar, Divam Gupta +1
We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-ob…
A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation
Dinesh Khandelwal, Suyash Agrawal, Parag Singla +1
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)…
U-SegNet: Fully Convolutional Neural Network based Automated Brain tissue segmentation Tool
Pulkit Kumar, Pravin Nagar, Chetan Arora +1
Automated brain tissue segmentation into white matter (WM), gray matter (GM), and cerebro-spinal fluid (CSF) from magnetic resonance images (MRI) is helpful in the diagnosis of neu…