PACL

Reported on 4 benchmarks across 1 task · 1 paper · 2 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 SegmentationonCityscape-171
mIoU· 2022-12-09
38.8
SOTA
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning arXiv:2212.04994
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2022-12-09
31.4
best: 38.2 (Mask-Adapter)
SOTA
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning arXiv:2212.04994
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· 2022-12-09
72.3
best: 97.9 (UMG-CLIP-L/14)
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning arXiv:2212.04994
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2022-12-09
50.1
best: 64.6 (HyperSeg)
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning arXiv:2212.04994