activity
20192023
most citedEncouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2023

Look Beyond Bias with Entropic Adversarial Data Augmentation

Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall +2

Deep neural networks do not discriminate between spurious and causal patterns, and will only learn the most predictive ones while ignoring the others. This shortcut learning behavi…

cs.LG2022

Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation

Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall +2

Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time ada…