activity
20182022
most citedInstance adaptive adversarial training: Improved accuracy tradeoffs in neural nets

65 citations · 115 across the 8 of their papers we have counts for

collaborators

13 papers

cs.CV20222 cited

A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes

Mazda Moayeri, Phillip Pope, Yogesh Balaji +1

While datasets with single-label supervision have propelled rapid advances in image classification, additional annotations are necessary in order to quantitatively assess how model…

cs.LG202112 cited

Understanding Overparameterization in Generative Adversarial Networks

Yogesh Balaji, Mohammadmahdi Sajedi, Neha Mukund Kalibhat +4

A broad class of unsupervised deep learning methods such as Generative Adversarial Networks (GANs) involve training of overparameterized models where the number of parameters of th…

cs.LG2020

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation

Yogesh Balaji, Rama Chellappa, Soheil Feizi

Optimal Transport (OT) distances such as Wasserstein have been used in several areas such as GANs and domain adaptation. OT, however, is very sensitive to outliers (samples with la…

cs.LG202018 cited

The Effectiveness of Memory Replay in Large Scale Continual Learning

Yogesh Balaji, Mehrdad Farajtabar, Dong Yin +2

We study continual learning in the large scale setting where tasks in the input sequence are not limited to classification, and the outputs can be of high dimension. Among multiple…

cs.LG2020

Winning Lottery Tickets in Deep Generative Models

Neha Mukund Kalibhat, Yogesh Balaji, Soheil Feizi

The lottery ticket hypothesis suggests that sparse, sub-networks of a given neural network, if initialized properly, can be trained to reach comparable or even better performance t…

cs.CV2020

Learning to Balance Specificity and Invariance for In and Out of Domain Generalization

Prithvijit Chattopadhyay, Yogesh Balaji, Judy Hoffman

We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to…