10-shot image generation on PASCAL Context-60

Metric: mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	mIoU▼	Extra Data	Paper	Date↕	Code
1	CorrCLIP	44.9	No	CorrCLIP: Reconstructing Correlations in CLIP wi...	2024-11-15	Code
2	TextRegion	41.2	No	TextRegion: Text-Aligned Region Tokens from Froz...	2025-05-29	Code
3	Trident	40.1	No	Harnessing Vision Foundation Models for High-Per...	2024-11-14	Code
4	ProxyCLIP	35.4	No	ProxyCLIP: Proxy Attention Improves CLIP for Ope...	2024-08-09	Code

#1CorrCLIPSOTA
44.9
mIoU· 2024-11-15
CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation Code
#2TextRegion
41.2
mIoU· 2025-05-29
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models Code
#3TridentSOTA
40.1
mIoU· 2024-11-14
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation Code
#4ProxyCLIPSOTA
35.4
mIoU· 2024-08-09
ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation Code