MAFT+

Reported on 6 benchmarks across 2 tasks · 1 paper

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

Computer Vision6 results

Open Vocabulary Panoptic SegmentationonADE20K
PQ· 2024-08-01
27.1
best: 31.6 (UMG-CLIP-E/14)
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation arXiv:2408.00744
Open Vocabulary Semantic SegmentationonADE20K-847
mIoU· 2024-08-01
15.1
best: 17.3 (UMG-CLIP-E/14)
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation arXiv:2408.00744
Open Vocabulary Semantic SegmentationonPASCAL Context-459
mIoU· 2024-08-01
21.6
best: 25.8 (SILC)
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation arXiv:2408.00744
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· 2024-08-01
96.5
best: 97.9 (UMG-CLIP-L/14)
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation arXiv:2408.00744
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2024-08-01
59.4
best: 64.6 (HyperSeg)
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation arXiv:2408.00744
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2024-08-01
36.1
best: 38.2 (Mask-Adapter)
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation arXiv:2408.00744