30 citations · 81 across the 32 of their papers we have counts for
3 papers · 1 filter
Unbiased Supervised Contrastive Learning
Carlo Alberto Barbano, Benoit Dufumier, Enzo Tartaglione +2
Many datasets are biased, namely they contain easy-to-learn features that are highly correlated with the target class only in the dataset but not in the true underlying distributio…
Optimizing transformations for contrastive learning in a differentiable framework
Camille Ruppli, Pietro Gori, Roberto Ardon +1
Current contrastive learning methods use random transformations sampled from a large list of transformations, with fixed hyperparameters, to learn invariance from an unannotated da…
Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels
Benoit Dufumier, Pietro Gori, Julie Victor +2
Contrastive Learning has shown impressive results on natural and medical images, without requiring annotated data. However, a particularity of medical images is the availability of…