ViTAE-B + RVSA-UperNet

Reported on 4 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.

Medical2 results

Semantic SegmentationonLoveDA
Category mIoU· 2022-08-08
52.44
best: 56.16 (U-Net (MaxViT-S))
SOTA
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987
Semantic SegmentationoniSAID
mIoU· 2022-08-08
64.49
best: 70.3 (SegNeXt-L)
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987

Audio2 results

10-shot image generationonLoveDA
Category mIoU· 2022-08-08
52.44
best: 56.16 (U-Net (MaxViT-S))
SOTA
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987
10-shot image generationoniSAID
mIoU· 2022-08-08
64.49
best: 70.3 (SegNeXt-L)
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987