OVSeg Swin-B

Reported on 5 benchmarks across 1 task · 1 paper · 5 SOTA

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

Computer Vision5 results

Open Vocabulary Semantic SegmentationonADE20K-847
mIoU· 2022-10-09
9
best: 17.3 (UMG-CLIP-E/14)
SOTA
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP arXiv:2210.04150
Open Vocabulary Semantic SegmentationonPASCAL Context-459
mIoU· 2022-10-09
12.4
best: 25.8 (SILC)
SOTA
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP arXiv:2210.04150
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· 2022-10-09
94.5
best: 97.9 (UMG-CLIP-L/14)
SOTA
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP arXiv:2210.04150
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2022-10-09
55.7
best: 64.6 (HyperSeg)
SOTA
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP arXiv:2210.04150
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2022-10-09
29.6
best: 38.2 (Mask-Adapter)
SOTA
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP arXiv:2210.04150