Mahmoud Assran
Graph View
Backlinks
- An Image is Worth More Than 16x16 Patches - Exploring Transformers on Individual Pixels
- DINOv2 - Learning Robust Visual Features without Supervision
- Intuitive physics understanding emerges from self-supervised pretraining on natural videos
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
- Stochastic positional embeddings improve masked image modeling
- The Hidden Uniform Cluster Prior in Self-Supervised Learning