TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Unsupervised Semantic Segmentation/COCO-Object

Unsupervised Semantic Segmentation on COCO-Object

Metric: mIoU (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕mIoU▼Extra DataPaperDate↕Code
1CorrCLIP49.4NoCorrCLIP: Reconstructing Correlations in CLIP wi...2024-11-15Code
2Trident42.2NoHarnessing Vision Foundation Models for High-Per...2024-11-14Code
3ProxyCLIP39.2NoProxyCLIP: Proxy Attention Improves CLIP for Ope...2024-08-09Code
4TTD (TCL)37.4NoTTD: Text-Tag Self-Distillation Enhancing Image-...2024-03-30Code
5CLS-SEG35.3NoTagCLIP: A Local-to-Global Framework to Enhance ...2023-12-20Code
6TagAlign33.3NoTagAlign: Improving Vision-Language Alignment wi...2023-12-21Code
7TCL31.6NoLearning to Generate Text-grounded Mask for Open...2022-12-01Code
8COSMOS ViT-B/1631.3NoCOSMOS: Cross-Modality Self-Distillation for Vis...2024-12-02Code
9GroupViT (RedCaps)27.5NoGroupViT: Semantic Segmentation Emerges from Tex...2022-02-22Code
10TTD (MaskCLIP)26.5NoTTD: Text-Tag Self-Distillation Enhancing Image-...2024-03-30Code
11MaskCLIP20.6NoExtract Free Dense Labels from CLIP2021-12-02Code
12ReCo15.7NoReCo: Retrieve and Co-segment for Zero-shot Tran...2022-06-14Code