Matcher(DINOv2)

Reported on 6 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

Few-Shot LearningonCOCO-20i (5-shot)
Mean IoU· 2023-05-22
60.7
best: 67.9 (SegGPT (ViT))
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching arXiv:2305.13310
Few-Shot LearningonCOCO-20i (1-shot)
Mean IoU· 2023-05-22
52.7
best: 59.4 (PGMA-Net (ResNet-101))
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching arXiv:2305.13310
Meta-LearningonCOCO-20i (5-shot)
Mean IoU· 2023-05-22
60.7
best: 67.9 (SegGPT (ViT))
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching arXiv:2305.13310
Meta-LearningonCOCO-20i (1-shot)
Mean IoU· 2023-05-22
52.7
best: 59.4 (PGMA-Net (ResNet-101))
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching arXiv:2305.13310

Computer Vision2 results

Few-Shot Semantic SegmentationonCOCO-20i (5-shot)
Mean IoU· 2023-05-22
60.7
best: 67.9 (SegGPT (ViT))
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching arXiv:2305.13310
Few-Shot Semantic SegmentationonCOCO-20i (1-shot)
Mean IoU· 2023-05-22
52.7
best: 59.4 (PGMA-Net (ResNet-101))
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching arXiv:2305.13310