EBSeg-L

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· 2024-06-14
13.7
best: 17.3 (UMG-CLIP-E/14)
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing arXiv:2406.09829
Open Vocabulary Semantic SegmentationonPASCAL Context-459
mIoU· 2024-06-14
21
best: 25.8 (SILC)
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing arXiv:2406.09829
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· 2024-06-14
96.4
best: 97.9 (UMG-CLIP-L/14)
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing arXiv:2406.09829
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2024-06-14
60.2
best: 64.6 (HyperSeg)
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing arXiv:2406.09829
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2024-06-14
32.8
best: 38.2 (Mask-Adapter)
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing arXiv:2406.09829