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/Panoptic Segmentation/Mapillary val

Panoptic Segmentation on Mapillary val

Metric: PQth (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕PQth▼Extra DataPaperDate↕Code
1Panoptic FCN* (Swin-L, single-scale)40.8NoFully Convolutional Networks for Panoptic Segmen...2020-12-01Code
2OneFormer (ConvNeXt-L, single-scale)40.6NoOneFormer: One Transformer to Rule Universal Ima...2022-11-10Code
3OneFormer (DiNAT-L, single-scale)40.5NoOneFormer: One Transformer to Rule Universal Ima...2022-11-10Code
4Panoptic-DeepLab (SWideRNet-(1, 1, 4.5), multi-scale)39.3NoScaling Wide Residual Networks for Panoptic Segm...2020-11-23-
5Mask2Former + Intra-Batch Supervision (ResNet-50)34.9NoIntra-Batch Supervision for Panoptic Segmentatio...2023-04-17Code
6Axial-DeepLab-L (multi-scale)33.4NoAxial-DeepLab: Stand-Alone Axial-Attention for P...2020-03-17Code
7Panoptic FCN* (ResNet-FPN)32.9NoFully Convolutional Networks for Panoptic Segmen...2020-12-01Code