HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Unsupervised Semantic Segmentation With 10

Metrics

mIoU

Results

Performance results of various models on this benchmark

Model Name
mIoU
Paper TitleRepository
CLS-SEG35.3TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training
ProxyCLIP39.2ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
TagAlign33.3TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
Trident42.2Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
TCL31.6Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs
COSMOS ViT-B/1631.3COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
TTD (TCL)37.4TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
TTD (MaskCLIP)26.5TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
MaskCLIP20.6Extract Free Dense Labels from CLIP
GroupViT (RedCaps)27.5GroupViT: Semantic Segmentation Emerges from Text Supervision
ReCo15.7ReCo: Retrieve and Co-segment for Zero-shot Transfer-
0 of 11 row(s) selected.