SegViT: Semantic Segmentation with Plain Vision Transformers
Open paper
Benchmark
Model
Rank
Results
semantic-segmentation-on-coco-stuff-test
SegViT (ours)
#4
mIoU: 50.3%
semantic-segmentation-on-pascal-context
SegViT (ours)
#5
mIoU: 65.3
semantic-segmentation-on-ade20k-val
SegViT ViT-Large
#30
mIoU: 55.2
Rank counts only results with a code link.