dino-vit-features
Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".
- 473
- Python
- MIT
- 4 y ago
Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".
[TPAMI'23] GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector.
[AAAI'23] Memory-aided Contrastive Consensus Learning for Co-salient Object Detection.
Single-image DINOv3 co-segmentation by click
Runs in the browser on Hugging Face