← Search

Rahul Rade

2 accepted papers

2022

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

ECCV 2022poster

"Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. To fix this vulnerability, prior works have built complex data augmentation strategies, combining multiple methods to enrich the training data. Ho…

2022

Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

ICLR 2022poster

While adversarial training has become the de facto approach for training robust classifiers, it leads to a drop in accuracy. This has led to prior works postulating that accuracy is inherently at odds with robustness. Yet, the phenomenon remains inexplicable. In this paper, we closely examine the ch…