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/Panoptic-DeepLab (X71)

Panoptic-DeepLab (X71)

Reported on 12 benchmarks across 3 tasks · 1 paper · 7 SOTA

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

Medical4 results

Semantic SegmentationonCityscapes val
PQ· uses extra data· 2019-11-22
64.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
Semantic SegmentationonMapillary val
PQ· 2019-11-22
40.5
best: 46.7 (OneFormer (DiNAT-L, single-scale))
SOTA
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
Semantic SegmentationonCityscapes val
AP· uses extra data· 2019-11-22
38.5
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
Semantic SegmentationonCityscapes val
mIoU· uses extra data· 2019-11-22
81.5
best: 90.3 (EfficientPS (Cityscapes-fine))
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194

Audio4 results

10-shot image generationonCityscapes val
PQ· uses extra data· 2019-11-22
64.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
10-shot image generationonMapillary val
PQ· 2019-11-22
40.5
best: 46.7 (OneFormer (DiNAT-L, single-scale))
SOTA
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
10-shot image generationonCityscapes val
AP· uses extra data· 2019-11-22
38.5
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
10-shot image generationonCityscapes val
mIoU· uses extra data· 2019-11-22
81.5
best: 90.3 (EfficientPS (Cityscapes-fine))
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194

Computer Vision4 results

Panoptic SegmentationonCityscapes val
PQ· uses extra data· 2019-11-22
64.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
Panoptic SegmentationonCityscapes val
mIoU· uses extra data· 2019-11-22
81.5
best: 90.3 (EfficientPS (Cityscapes-fine))
SOTA
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
Panoptic SegmentationonMapillary val
PQ· 2019-11-22
40.5
best: 46.7 (OneFormer (DiNAT-L, single-scale))
SOTA
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194
Panoptic SegmentationonCityscapes val
AP· uses extra data· 2019-11-22
38.5
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation arXiv:1911.10194