MAFT-ViTL

Reported on 5 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 Vision6 results

Open Vocabulary Semantic SegmentationonADE20K-847
mIoU· 2023-09-30
12.1
best: 17.3 (UMG-CLIP-E/14)
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation arXiv:2310.00240
Open Vocabulary Semantic SegmentationonPASCAL Context-459
mIoU· 2023-09-30
15.7
best: 25.8 (SILC)
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation arXiv:2310.00240
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· 2023-09-30
92.1
best: 97.9 (UMG-CLIP-L/14)
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation arXiv:2310.00240
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· 2023-09-30
92.1
best: 97.9 (UMG-CLIP-L/14)
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation arXiv:2310.00240
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2023-09-30
58.5
best: 64.6 (HyperSeg)
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation arXiv:2310.00240
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2023-09-30
32
best: 38.2 (Mask-Adapter)
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation arXiv:2310.00240