Author

Maxime Oquab

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Scalable Patch-Level Self-Supervised Learning

Self-supervised learning (SSL) at scale produces powerful visual representations. However, most scalable SSL methods rely on ad hoc combinations of multiple objectives and stabilization mechanisms. Taking a step back, we ask if we can design a high-performing, yet principled SSL algorithm. Starting from the multi-view...

Maximilian Seitzer, Gabriele Trivigno, Antonín Vobecký et al. · 0 citations

Open access May 2024

Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning

RayDINO is introduced, a self-supervised chest X-ray foundation model trained on 840,000 images, that outperforms supervised methods across nine radiology tasks and shows improved generalization and reduced bias across demographics.

Théo Moutakanni, P. Bojanowski, G. Chassagnon et al. · Nature Communications · 28 citations · ⚡1