Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/CMT-DeepLab (MaX-S, single-scale, IN-1K)

CMT-DeepLab (MaX-S, single-scale, IN-1K)

Reported on 6 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Semantic SegmentationonCityscapes val
PQ· 2022-06-17
64.6
best: 70.8 (ViT-P (OneFormer, InternImage-H))
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation arXiv:2206.08948
Semantic SegmentationonCityscapes val
mIoU· 2022-06-17
81.4
best: 90.3 (EfficientPS (Cityscapes-fine))
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation arXiv:2206.08948

Audio2 results

10-shot image generationonCityscapes val
PQ· 2022-06-17
64.6
best: 70.8 (ViT-P (OneFormer, InternImage-H))
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation arXiv:2206.08948
10-shot image generationonCityscapes val
mIoU· 2022-06-17
81.4
best: 90.3 (EfficientPS (Cityscapes-fine))
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation arXiv:2206.08948

Computer Vision2 results

Panoptic SegmentationonCityscapes val
PQ· 2022-06-17
64.6
best: 70.8 (ViT-P (OneFormer, InternImage-H))
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation arXiv:2206.08948
Panoptic SegmentationonCityscapes val
mIoU· 2022-06-17
81.4
best: 90.3 (EfficientPS (Cityscapes-fine))
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation arXiv:2206.08948