164 citations · 491 across the 15 of their papers we have counts for
5 papers · 1 filter
Improving Network Robustness against Adversarial Attacks with Compact Convolution
Rajeev Ranjan, Swami Sankaranarayanan, Carlos D. Castillo +1
Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by advers…
Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
Swami Sankaranarayanan, Yogesh Balaji, Arpit Jain +2
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 represe…
Regularizing deep networks using efficient layerwise adversarial training
Swami Sankaranarayanan, Arpit Jain, Rama Chellappa +1
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…
Generate To Adapt: Aligning Domains using Generative Adversarial Networks
Swami Sankaranarayanan, Yogesh Balaji, Carlos D. Castillo +1
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 distrib…
Self corrective Perturbations for Semantic Segmentation and Classification
Swami Sankaranarayanan, Arpit Jain, Ser Nam Lim
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 performa…