MaskCLIP++

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 Vision5 results

Open Vocabulary Semantic SegmentationonADE20K-847
mIoU· 2024-12-16
16.8
best: 17.3 (UMG-CLIP-E/14)
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation arXiv:2412.11464
Open Vocabulary Semantic SegmentationonPASCAL Context-459
mIoU· 2024-12-16
23.9
best: 25.8 (SILC)
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation arXiv:2412.11464
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· 2024-12-16
96.8
best: 97.9 (UMG-CLIP-L/14)
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation arXiv:2412.11464
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2024-12-16
62.5
best: 64.6 (HyperSeg)
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation arXiv:2412.11464
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2024-12-16
38.2
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation arXiv:2412.11464