#17: CAPI: Cluster & Predict Patches for Improved Image Modeling by T. Darcet

Join our free BLISS Speaker Series Summer 2025!

We are excited to feature Timothée Darcet, PhD student at Meta AI and Inria, who will discuss "CAPI: Cluster and Predict Latent Patches for Improved Masked Image Modeling", lasting approximately 45 minutes. After the talk, seize the opportunity to connect with fellow AI enthusiasts to share ideas and questions while enjoying free drinks. Door close by 7.15pm, so please come early! Also, "attend"ing (RSVP) here on Meetup is strictly necessary to be guaranteed entry.
Please note that Meetup has recently been quite keen on promoting its Plus program. However, you are not obligated to purchase it, as both our events and the platform remain free.

Who is this event for?
This event is open to everyone interested in state-of-the-art AI research. We especially design it for students, PhD candidates, academic researchers, and industry professionals with a research focus in machine learning.

Abstract: Masked Image Modeling (MIM) offers a promising approach to self-supervised representation learning, however existing MIM models still lag behind the state-of-the-art. In this talk, we systematically analyze target representations, loss functions, and architectures, to present CAPI - a novel pure-MIM framework that relies on the prediction of latent clusterings. Our approach leverages a clustering-based loss, which is stable to train, and exhibits promising scaling properties. Our ViT-L backbone, CAPI, achieves 83.8% accuracy on ImageNet and 32.1% mIoU on ADE20K with simple linear probes, substantially outperforming previous MIM methods and approaching the performance of the current state-of-the-art, DINOv2.

We are BLISS e.V., the AI organization in Berlin that connects like-minded individuals who share great interest and passion for the field of machine learning. This summer 2025, we will host an exciting speaker series on site in Berlin, featuring excellent researchers from Merantix Momentum, Meta AI, Inria, Microsoft AI4Science, Google DeepMind, and University of Oxford.
Website: https://bliss.berlin
Youtube: https://www.youtube.com/@bliss.ev.berlin

Disclaimer: By attending this event you agree to be photographed.