Mathilde Caron
Graph View
Backlinks
- Emerging Properties in Self-Supervised Vision Transformers
- FlexiViT - One Model for All Patch Sizes
- Location-Aware Self-Supervised Transformers for Semantic Segmentation
- Pano3D - Unified 3D Reconstruction and Panoptic Segmentation
- Temporal Chain of Thought - Long-Video Understanding by Thinking in Frames
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- What Mechanisms Does Knowledge Distillation Distill