SILC

Reported on 6 benchmarks across 1 task · 1 paper · 3 SOTA

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 SegmentationonPASCAL Context-459
mIoU· 2023-10-20
25.8
SOTA
SILC: Improving Vision Language Pretraining with Self-Distillation arXiv:2310.13355
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· 2023-10-20
97.6
best: 97.9 (UMG-CLIP-L/14)
SOTA
SILC: Improving Vision Language Pretraining with Self-Distillation arXiv:2310.13355
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2023-10-20
63.5
best: 64.6 (HyperSeg)
SOTA
SILC: Improving Vision Language Pretraining with Self-Distillation arXiv:2310.13355
Open Vocabulary Semantic SegmentationonADE20K-847
mIoU· 2023-10-20
15
best: 17.3 (UMG-CLIP-E/14)
SILC: Improving Vision Language Pretraining with Self-Distillation arXiv:2310.13355
Open Vocabulary Semantic SegmentationonPascalVOC-20b
mIoU· 2023-10-20
82.5
best: 85.4 (UMG-CLIP-E/14)
SILC: Improving Vision Language Pretraining with Self-Distillation arXiv:2310.13355
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2023-10-20
37.7
best: 38.2 (Mask-Adapter)
SILC: Improving Vision Language Pretraining with Self-Distillation arXiv:2310.13355