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/Open Vocabulary Panoptic Segmentation/ADE20K

Open Vocabulary Panoptic Segmentation on ADE20K

Metric: PQ (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕PQ▼Extra DataPaperDate↕Code
1UMG-CLIP-E/1431.6NoUMG-CLIP: A Unified Multi-Granularity Vision Gen...2024-01-12Code
2PosSAM29.2NoPosSAM: Panoptic Open-vocabulary Segment Anything2024-03-14Code
3UMG-CLIP-L/1429.1NoUMG-CLIP: A Unified Multi-Granularity Vision Gen...2024-01-12Code
4MAFT+27.1NoCollaborative Vision-Text Representation Optimiz...2024-08-01Code
5FC-CLIP26.8NoConvolutions Die Hard: Open-Vocabulary Segmentat...2023-08-04Code
6CLIPSelf23.7NoCLIPSelf: Vision Transformer Distills Itself for...2023-10-02Code
7ODISE(Caption)23.4NoOpen-Vocabulary Panoptic Segmentation with Text-...2023-03-08Code
8ODISE (Label)22.6NoOpen-Vocabulary Panoptic Segmentation with Text-...2023-03-08Code
9FreeSeg16.3NoFreeSeg: Unified, Universal and Open-Vocabulary ...2023-03-30-
10MaskCLIP15.1NoExtract Free Dense Labels from CLIP2021-12-02Code