OpenCodePapers

unsupervised-semantic-segmentation-with-4

Semantic SegmentationUnsupervised Semantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-training
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeMean IoU (val)ModelNameReleaseDate
CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation✓ Link30.7CorrCLIP2024-11-15
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models✓ Link27.3TextRegion2025-05-29
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation✓ Link26.7Trident2024-11-14
ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation✓ Link24.2ProxyCLIP2024-08-09
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training✓ Link17.7COSMOS ViT-B/162024-12-02
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification✓ Link17.3TagAlign2023-12-21
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs✓ Link17.1TCL2022-12-01
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias✓ Link17.0TTD (TCL)2024-03-30
Perceptual Grouping in Contrastive Vision-Language Models✓ Link13.5CLIPpy ViT-B2022-10-18
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias✓ Link12.7TTD (MaskCLIP)2024-03-30
ReCo: Retrieve and Co-segment for Zero-shot Transfer✓ Link11.2ReCo2022-06-14
Extract Free Dense Labels from CLIP✓ Link9.8MaskCLIP2021-12-02
GroupViT: Semantic Segmentation Emerges from Text Supervision✓ Link9.2GroupViT (RedCaps)2022-02-22
Check out how to contribute new results.