OTSeg

Reported on 4 benchmarks across 1 task · 1 paper

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

Computer Vision4 results

Zero-Shot Semantic SegmentationonPASCAL VOC
Inductive Setting hIoU· 2024-03-21
84.5
best: 88.4 (CLIP-RC)
OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation arXiv:2403.14183
Zero-Shot Semantic SegmentationonPASCAL VOC
Transductive Setting hIoU· 2024-03-21
94.2
best: 94.4 (OTSeg+)
OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation arXiv:2403.14183
Zero-Shot Semantic SegmentationonCOCO-Stuff
Inductive Setting hIoU· 2024-03-21
41.4
best: 41.5 (OTSeg+)
OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation arXiv:2403.14183
Zero-Shot Semantic SegmentationonCOCO-Stuff
Transductive Setting hIoU· 2024-03-21
49.5
best: 49.8 (OTSeg+)
OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation arXiv:2403.14183