ZegFormer

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision4 results

Open Vocabulary Semantic SegmentationonCOCO-Stuff-171
HIoU· 2021-12-15
34.8
best: 39.1 (POMP)
SOTA
Decoupling Zero-Shot Semantic Segmentation arXiv:2112.07910
Open Vocabulary Semantic SegmentationonPascalVOC-20
hIoU· 2021-12-15
73.3
best: 84.4 (POMP)
SOTA
Decoupling Zero-Shot Semantic Segmentation arXiv:2112.07910
Zero-Shot Semantic SegmentationonPASCAL VOC
Inductive Setting hIoU· 2021-12-15
73.3
best: 88.4 (CLIP-RC)
SOTA
Decoupling Zero-Shot Semantic Segmentation arXiv:2112.07910
Zero-Shot Semantic SegmentationonCOCO-Stuff
Inductive Setting hIoU· 2021-12-15
33.2
best: 41.5 (OTSeg+)
SOTA
Decoupling Zero-Shot Semantic Segmentation arXiv:2112.07910