Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings
David Restrepo, Miguel L Martins, Chenwei Wu +5
Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contri…
cs.LG2024
You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
Théo Moutakanni, Maxime Oquab, Marc Szafraniec +2
Self-Supervised learning (SSL) with Joint-Embedding Architectures (JEA) has led to outstanding performances. All instantiations of this paradigm were trained using strong and well-…