HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Unsupervised Semantic Segmentation With 7

Metrics

mIoU

Results

Performance results of various models on this benchmark

Paper TitleRepository
Trident88.7Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
TagAlign87.9TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
ProxyCLIP83.3ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
TCL83.2Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs
GroupViT (RedCaps)79.7GroupViT: Semantic Segmentation Emerges from Text Supervision
COSMOS ViT-B/1677.7COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
MaskCLIP74.9Extract Free Dense Labels from CLIP
ReCo57.7ReCo: Retrieve and Co-segment for Zero-shot Transfer
0 of 8 row(s) selected.
Unsupervised Semantic Segmentation With 7 | SOTA | HyperAI