Publications
Diverse Weight Averaging for Out-of-Distribution Generalization
To improve out-of-distribution generalization, we average diverse weights obtained from different training runs; this strategy is motivated by an extension of the bias-variance theory to weight averaging and is state-of-the-art on …
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks
We introduce a new generalized framework for learning multi-input multi-output subnetworks and study how to best mix the inputs. We obtain sota on CIFAR and Tiny ImageNet by better leveraging the expressiveness of large networks.
DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
Driven by arguments from information theory, we introduce a new learning strategy for deep ensembles that increases diversity among members: we adversarially prevent features from being conditionally redundant.
CORE: Color Regression for Multiple Colors Fashion Garments
We detect continuous colors for fashion garments using a new architecture.
Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction
We present a method to learn a visual representation adapted for e-commerce products.