PatchDiverse + Swin-L (multi-scale test, upernet, ImageNet22k pretrain)

Reported on 2 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Medical1 result

Semantic SegmentationonADE20K
Validation mIoU· 2021-04-26
54.4
best: 63.6 (ViT-P (InternImage-H))
SOTA
Vision Transformers with Patch Diversification arXiv:2104.12753

Audio1 result

10-shot image generationonADE20K
Validation mIoU· 2021-04-26
54.4
best: 63.6 (ViT-P (InternImage-H))
SOTA
Vision Transformers with Patch Diversification arXiv:2104.12753