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/kMaX-DeepLab (single-scale)

kMaX-DeepLab (single-scale)

Reported on 30 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Medical10 results

Semantic SegmentationonCOCO test-dev
PQst· 2022-07-08
49
best: 58.9 (MaskConver (ResNet50, single-scale))
SOTA
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCityscapes test
PQ· 2022-07-08
66.2
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCityscapes val
AP· 2022-07-08
44
best: 50.6 (ViT-P (OneFormer, InternImage-H))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCityscapes val
PQ· 2022-07-08
68.4
best: 70.8 (ViT-P (OneFormer, InternImage-H))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCityscapes val
mIoU· 2022-07-08
83.5
best: 90.3 (EfficientPS (Cityscapes-fine))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCOCO test-dev
PQ· 2022-07-08
58.5
best: 59.5 (Mask DINO (single scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCOCO test-dev
PQth· 2022-07-08
64.8
best: 65.1 (Mask2Former (Swin-L))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCOCO minival
PQ· 2022-07-08
57.9
best: 61.2 (HyperSeg (Swin-B))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCOCO minival
PQst· 2022-07-08
48.6
best: 49.2 (OneFormer (InternImage-H,single-scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Semantic SegmentationonCOCO minival
PQth· 2022-07-08
64
best: 67.1 (OneFormer (InternImage-H,single-scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044

Audio10 results

10-shot image generationonCOCO test-dev
PQst· 2022-07-08
49
best: 58.9 (MaskConver (ResNet50, single-scale))
SOTA
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCityscapes test
PQ· 2022-07-08
66.2
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCityscapes val
AP· 2022-07-08
44
best: 50.6 (ViT-P (OneFormer, InternImage-H))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCityscapes val
PQ· 2022-07-08
68.4
best: 70.8 (ViT-P (OneFormer, InternImage-H))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCityscapes val
mIoU· 2022-07-08
83.5
best: 90.3 (EfficientPS (Cityscapes-fine))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCOCO test-dev
PQ· 2022-07-08
58.5
best: 59.5 (Mask DINO (single scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCOCO test-dev
PQth· 2022-07-08
64.8
best: 65.1 (Mask2Former (Swin-L))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCOCO minival
PQ· 2022-07-08
57.9
best: 61.2 (HyperSeg (Swin-B))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCOCO minival
PQst· 2022-07-08
48.6
best: 49.2 (OneFormer (InternImage-H,single-scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
10-shot image generationonCOCO minival
PQth· 2022-07-08
64
best: 67.1 (OneFormer (InternImage-H,single-scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044

Computer Vision10 results

Panoptic SegmentationonCOCO test-dev
PQst· 2022-07-08
49
best: 58.9 (MaskConver (ResNet50, single-scale))
SOTA
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCityscapes test
PQ· 2022-07-08
66.2
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCityscapes val
AP· 2022-07-08
44
best: 50.6 (ViT-P (OneFormer, InternImage-H))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCityscapes val
PQ· 2022-07-08
68.4
best: 70.8 (ViT-P (OneFormer, InternImage-H))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCityscapes val
mIoU· 2022-07-08
83.5
best: 90.3 (EfficientPS (Cityscapes-fine))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCOCO test-dev
PQ· 2022-07-08
58.5
best: 59.5 (Mask DINO (single scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCOCO test-dev
PQth· 2022-07-08
64.8
best: 65.1 (Mask2Former (Swin-L))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCOCO minival
PQ· 2022-07-08
57.9
best: 61.2 (HyperSeg (Swin-B))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCOCO minival
PQst· 2022-07-08
48.6
best: 49.2 (OneFormer (InternImage-H,single-scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044
Panoptic SegmentationonCOCO minival
PQth· 2022-07-08
64
best: 67.1 (OneFormer (InternImage-H,single-scale))
kMaX-DeepLab: k-means Mask Transformer arXiv:2207.04044