HyperAIHyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAIHyperAI

Unsupervised Semantic Segmentation With 11

Métriques

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
mIoU
Paper TitleRepository
TTD (TCL)61.1TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias-
TCL55.0Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs-
CLS-SEG68.7TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training-
Trident70.8Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation-
MaskCLIP29.3Extract Free Dense Labels from CLIP-
TagAlign53.9TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification-
TTD (MaskCLIP)43.1TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias-
ProxyCLIP65.0ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation-
0 of 8 row(s) selected.
Unsupervised Semantic Segmentation With 11 | SOTA | HyperAI