429 citations · 664 across the 34 of their papers we have counts for
4 papers · 1 filter
The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration
Bingyuan Liu, Ismail Ben Ayed, Adrian Galdran +1
In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can…
Segmentation with mixed supervision: Confidence maximization helps knowledge distillation
Bingyuan Liu, Christian Desrosiers, Ismail Ben Ayed +1
Despite achieving promising results in a breadth of medical image segmentation tasks, deep neural networks require large training datasets with pixel-wise annotations. Obtaining th…
Adversarial Robustness via Fisher-Rao Regularization
Marine Picot, Francisco Messina, Malik Boudiaf +3
Adversarial robustness has become a topic of growing interest in machine learning since it was observed that neural networks tend to be brittle. We propose an information-geometric…
Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses
Bingyuan Liu, Jose Dolz, Adrian Galdran +2
Most segmentation losses are arguably variants of the Cross-Entropy (CE) or Dice losses. On the surface, these two categories of losses seem unrelated, and there is no clear consen…