Label Anything (ViT-B/16-MAE)

Reported on 3 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.

Methodology2 results

Few-Shot LearningonCOCO-20i (2-way 1-shot)
mIoU· 2024-07-02
31.9
best: 34.6 (Label Anything (Vit-B/16-SAM))
Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts arXiv:2407.02075
Meta-LearningonCOCO-20i (2-way 1-shot)
mIoU· 2024-07-02
31.9
best: 34.6 (Label Anything (Vit-B/16-SAM))
Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts arXiv:2407.02075

Computer Vision1 result

Few-Shot Semantic SegmentationonCOCO-20i (2-way 1-shot)
mIoU· 2024-07-02
31.9
best: 34.6 (Label Anything (Vit-B/16-SAM))
Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts arXiv:2407.02075