CLIP-RC

Reported on 4 benchmarks across 1 task

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
88.4
Zero-Shot Semantic SegmentationonPASCAL VOC
Transductive Setting hIoU
93
best: 94.4 (OTSeg+)
Zero-Shot Semantic SegmentationonCOCO-Stuff
Inductive Setting hIoU
41.2
best: 41.5 (OTSeg+)
Zero-Shot Semantic SegmentationonCOCO-Stuff
Transductive Setting hIoU
49.7
best: 49.8 (OTSeg+)