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/Axial-DeepLab-L (multi-scale)

Axial-DeepLab-L (multi-scale)

Reported on 24 benchmarks across 3 tasks · 1 paper · 15 SOTA

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

Medical8 results

Semantic SegmentationonMapillary val
PQ· 2020-03-17
41.1
best: 46.7 (OneFormer (DiNAT-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonMapillary val
PQst· 2020-03-17
51.3
best: 54.9 (OneFormer (DiNAT-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonMapillary val
PQth· 2020-03-17
33.4
best: 40.8 (Panoptic FCN* (Swin-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonMapillary val
mIoU· 2020-03-17
58.4
best: 76 (AO-SegNet)
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonCOCO minival
PQ· 2020-03-17
43.9
best: 61.2 (HyperSeg (Swin-B))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonCOCO test-dev
PQ· 2020-03-17
44.2
best: 59.5 (Mask DINO (single scale))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonCOCO test-dev
PQst· 2020-03-17
36.8
best: 58.9 (MaskConver (ResNet50, single-scale))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonCOCO test-dev
PQth· 2020-03-17
49.2
best: 65.1 (Mask2Former (Swin-L))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853

Audio8 results

10-shot image generationonMapillary val
PQ· 2020-03-17
41.1
best: 46.7 (OneFormer (DiNAT-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonMapillary val
PQst· 2020-03-17
51.3
best: 54.9 (OneFormer (DiNAT-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonMapillary val
PQth· 2020-03-17
33.4
best: 40.8 (Panoptic FCN* (Swin-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonMapillary val
mIoU· 2020-03-17
58.4
best: 76 (AO-SegNet)
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonCOCO minival
PQ· 2020-03-17
43.9
best: 61.2 (HyperSeg (Swin-B))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonCOCO test-dev
PQ· 2020-03-17
44.2
best: 59.5 (Mask DINO (single scale))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonCOCO test-dev
PQst· 2020-03-17
36.8
best: 58.9 (MaskConver (ResNet50, single-scale))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonCOCO test-dev
PQth· 2020-03-17
49.2
best: 65.1 (Mask2Former (Swin-L))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853

Computer Vision8 results

Panoptic SegmentationonMapillary val
PQ· 2020-03-17
41.1
best: 46.7 (OneFormer (DiNAT-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonMapillary val
PQst· 2020-03-17
51.3
best: 54.9 (OneFormer (DiNAT-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonMapillary val
PQth· 2020-03-17
33.4
best: 40.8 (Panoptic FCN* (Swin-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonMapillary val
mIoU· 2020-03-17
58.4
best: 61.7 (OneFormer (DiNAT-L, single-scale))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonCOCO minival
PQ· 2020-03-17
43.9
best: 61.2 (HyperSeg (Swin-B))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonCOCO test-dev
PQ· 2020-03-17
44.2
best: 59.5 (Mask DINO (single scale))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonCOCO test-dev
PQst· 2020-03-17
36.8
best: 58.9 (MaskConver (ResNet50, single-scale))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonCOCO test-dev
PQth· 2020-03-17
49.2
best: 65.1 (Mask2Former (Swin-L))
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853