2 papers
cs.CV2026
CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals
Rémi Kazmierczak, Johanne Cohen, Marianne Clausel
Concept Bottleneck Models (CBMs) built on vision-language models such as CLIP represent a latent space as human-understandable concepts. These representations are unfaithful: relat…
stat.ML2025
Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach
Nicolas Atienza, Christophe Labreuche, Johanne Cohen +1
This paper introduces a novel method, Sample-efficient Probabilistic Detection using Extreme Value Theory (SPADE), which transforms a classifier into an abstaining classifier, offe…