DaViT-T

Reported on 4 benchmarks across 4 tasks · 1 paper

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

Medical2 results

Semantic SegmentationonADE20K
Validation mIoU· 2022-04-07
46.3
best: 63.6 (ViT-P (InternImage-H))
DaViT: Dual Attention Vision Transformers arXiv:2204.03645
Medical Image ClassificationonImageNet
GFLOPs· 2022-04-07
4.5
best: 8.8 (DaViT-S)
DaViT: Dual Attention Vision Transformers arXiv:2204.03645

Methodology1 result

ClassificationonImageNet
GFLOPs· 2022-04-07
4.5
best: 8.8 (DaViT-S)
DaViT: Dual Attention Vision Transformers arXiv:2204.03645

Audio1 result

10-shot image generationonADE20K
Validation mIoU· 2022-04-07
46.3
best: 63.6 (ViT-P (InternImage-H))
DaViT: Dual Attention Vision Transformers arXiv:2204.03645