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/Video Instance Segmentation/Youtube-VIS 2022 Validation

Video Instance Segmentation on Youtube-VIS 2022 Validation

Metric: mAP_L (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕mAP_L▼Extra DataPaperDate↕Code
1DVIS++(VIT-L)50.9YesDVIS++: Improved Decoupled Framework for Univers...2023-12-20Code
2CAVIS (VIT-L)48.6YesContext-Aware Video Instance Segmentation2024-07-03Code
3CTVIS (Swin-L)46.4YesCTVIS: Consistent Training for Online Video Inst...2023-07-24Code
4DVIS(Swin-L)45.9YesDVIS: Decoupled Video Instance Segmentation Fram...2023-06-06Code
5CTVIS (ResNet-50)39.4YesCTVIS: Consistent Training for Online Video Inst...2023-07-24Code
6InstanceFormer (Swin)26.3YesInstanceFormer: An Online Video Instance Segment...2022-08-22Code
7InstanceFormer (Resnet-50)24.8YesInstanceFormer: An Online Video Instance Segment...2022-08-22Code