SETR (ViT-Large)

Reported on 4 benchmarks across 2 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 SegmentationonUrbanLF
mIoU (Real)· 2020-12-31
77.74
best: 83.22 (CMNeXt (RGB-LF8))
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers arXiv:2012.15840
Semantic SegmentationonUrbanLF
mIoU (Syn)· 2020-12-31
77.69
best: 81.02 (CMNeXt (RGB-LF80))
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers arXiv:2012.15840

Audio2 results

10-shot image generationonUrbanLF
mIoU (Real)· 2020-12-31
77.74
best: 83.22 (CMNeXt (RGB-LF8))
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers arXiv:2012.15840
10-shot image generationonUrbanLF
mIoU (Syn)· 2020-12-31
77.69
best: 81.02 (CMNeXt (RGB-LF80))
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers arXiv:2012.15840