SegFormer (MiT-B3)

Reported on 4 benchmarks across 2 tasks · 2 papers

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

Medical2 results

Semantic SegmentationonCEMS-W
mIoU· 2023-09-15
83.34
best: 84.94 (UPerNet (RN50))
Robust Burned Area Delineation through Multitask Learning arXiv:2309.08368
Semantic SegmentationonDADA-seg
mIoU· 2021-05-31
27
best: 46.97 (MMUDA)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203

Audio2 results

10-shot image generationonCEMS-W
mIoU· 2023-09-15
83.34
best: 84.94 (UPerNet (RN50))
Robust Burned Area Delineation through Multitask Learning arXiv:2309.08368
10-shot image generationonDADA-seg
mIoU· 2021-05-31
27
best: 46.97 (MMUDA)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203