OpenCodePapers

unsupervised-semantic-segmentation-with-3

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.
PaperCodemIoUpixel accuracyModelNameReleaseDate
CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation✓ Link51.1CorrCLIP2024-11-15
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation✓ Link47.6Trident2024-11-14
ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation✓ Link42.0ProxyCLIP2024-08-09
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training✓ Link34.7COSMOS ViT-B/162024-12-02
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias✓ Link32.0TTD (MaskCLIP)2024-03-30
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification✓ Link27.5TagAlign2023-12-21
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias✓ Link27.0TTD (TCL)2024-03-30
ReCo: Retrieve and Co-segment for Zero-shot Transfer✓ Link24.283.7ReCo+2022-06-14
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs✓ Link24.0TCL2022-12-01
ReCo: Retrieve and Co-segment for Zero-shot Transfer✓ Link19.374.6ReCo2022-06-14
Perceptual Grouping in Contrastive Vision-Language Models✓ Link18.1CLIPpy ViT-B2022-10-18
Extract Free Dense Labels from CLIP✓ Link10.035.9MaskCLIP2021-12-02
Check out how to contribute new results.