Piotr Bojanowski
Graph View
Backlinks
- Back to the Features - DINO as a Foundation for Video World Models
- Cluster and Predict Latents Patches for Improved Masked Image Modeling
- DINOv2 - Learning Robust Visual Features without Supervision
- Emerging Properties in Self-Supervised Vision Transformers
- Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
- The Hidden Uniform Cluster Prior in Self-Supervised Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- V-JEPA 2 - Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Vision Transformers Need Registers