← Search

Sandesh Kamath

3 accepted papers

2024

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

CVPR 2024poster

Continual learning methods are known to suffer from catastrophic forgetting a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore to reduce potential drift in the feature extractor existing exemplar-free methods are typically evaluated…

2024

Rethinking Robustness of Model Attributions

AAAI 2024technical

For machine learning models to be reliable and trustworthy, their decisions must be interpretable. As these models find increasing use in safety-critical applications, it is important that not just the model predictions but also their explanations (as feature attributions) be robust to small human-i…

2021

Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks

NeurIPS 2021poster

(Non-)robustness of neural networks to small, adversarial pixel-wise perturbations, and as more recently shown, to even random spatial transformations (e.g., translations, rotations) entreats both theoretical and empirical understanding. Spatial robustness to random translations and rotations is com…