HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Unsupervised Semantic Segmentation With 3

Metrics

mIoU

Results

Performance results of various models on this benchmark

Model Name
mIoU
Paper TitleRepository
TCL24.0Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs-
TTD (MaskCLIP)32.0TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias-
ReCo+24.2ReCo: Retrieve and Co-segment for Zero-shot Transfer-
CLIPpy ViT-B18.1Perceptual Grouping in Contrastive Vision-Language Models-
MaskCLIP10.0Extract Free Dense Labels from CLIP-
Trident47.6Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation-
ReCo19.3ReCo: Retrieve and Co-segment for Zero-shot Transfer-
TTD (TCL)27.0TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias-
COSMOS ViT-B/1634.7COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training-
ProxyCLIP42.0ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation-
TagAlign27.5TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification-
0 of 11 row(s) selected.
Unsupervised Semantic Segmentation With 3 | SOTA | HyperAI