Semantic Segmentation on COCO minival

Metric: PQst (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	PQst▼	Extra Data	Paper	Date↕	Code
1	OneFormer (InternImage-H,single-scale)	49.2	No	OneFormer: One Transformer to Rule Universal Ima...	2022-11-10	Code
2	DiNAT-L (single-scale, Mask2Former)	48.8	No	Dilated Neighborhood Attention Transformer	2022-09-29	Code
3	kMaX-DeepLab (single-scale, pseudo-labels)	48.8	Yes	kMaX-DeepLab: k-means Mask Transformer	2022-07-08	Code
4	kMaX-DeepLab (single-scale, drop query with 256 queries)	48.6	No	kMaX-DeepLab: k-means Mask Transformer	2022-07-08	Code
5	kMaX-DeepLab (single-scale)	48.6	No	kMaX-DeepLab: k-means Mask Transformer	2022-07-08	Code
6	ViT-Adapter-L (single-scale, BEiTv2 pretrain, Mask2Former)	48.4	No	Vision Transformer Adapter for Dense Predictions	2022-05-17	Code
7	OneFormer (DiNAT-L, single-scale)	48.4	No	OneFormer: One Transformer to Rule Universal Ima...	2022-11-10	Code
8	Visual Attention Network (VAN-B6 + Mask2Former)	48.2	No	Visual Attention Network	2022-02-20	Code
9	Mask2Former (single-scale)	48.1	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
10	OneFormer (Swin-L, single-scale)	48	No	OneFormer: One Transformer to Rule Universal Ima...	2022-11-10	Code
11	Panoptic SegFormer (single-scale)	46.9	No	Panoptic SegFormer: Delving Deeper into Panoptic...	2021-09-08	Code
12	CMT-DeepLab (single-scale)	46.6	No	CMT-DeepLab: Clustering Mask Transformers for Pa...	2022-06-17	Code
13	MaskFormer (single-scale)	44	No	Per-Pixel Classification is Not All You Need for...	2021-07-13	Code
14	Panoptic SegFormer (ResNet-101)	43.2	No	Panoptic SegFormer: Delving Deeper into Panoptic...	2021-09-08	Code
15	MaX-DeepLab-L (single-scale)	42.2	No	MaX-DeepLab: End-to-End Panoptic Segmentation wi...	2020-12-01	Code
16	PanopticFPN+ResNeSt(single-scale)	37	No	ResNeSt: Split-Attention Networks	2020-04-19	Code
17	DETR-R101 (ResNet-101)	37	No	End-to-End Object Detection with Transformers	2020-05-26	Code
18	Axial-DeepLab-L(multi-scale)	36.8	No	Axial-DeepLab: Stand-Alone Axial-Attention for P...	2020-03-17	Code
19	Panoptic FCN* (ResNet-50-FPN)	35.6	No	Fully Convolutional Networks for Panoptic Segmen...	2020-12-01	Code
20	Axial-DeepLab-L (single-scale)	35.6	No	Axial-DeepLab: Stand-Alone Axial-Attention for P...	2020-03-17	Code
21	PanopticFPN++	33.6	No	End-to-End Object Detection with Transformers	2020-05-26	Code

#1OneFormer (InternImage-H,single-scale)SOTA
49.2
PQst· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation Code
#2DiNAT-L (single-scale, Mask2Former)
48.8
PQst· 2022-09-29
Dilated Neighborhood Attention Transformer Code
#3kMaX-DeepLab (single-scale, pseudo-labels)SOTA
48.8
PQst· Extra Data· 2022-07-08
kMaX-DeepLab: k-means Mask Transformer Code
#4kMaX-DeepLab (single-scale, drop query with 256 queries)
48.6
PQst· 2022-07-08
kMaX-DeepLab: k-means Mask Transformer Code
#5kMaX-DeepLab (single-scale)
48.6
PQst· 2022-07-08
kMaX-DeepLab: k-means Mask Transformer Code
#6ViT-Adapter-L (single-scale, BEiTv2 pretrain, Mask2Former)SOTA
48.4
PQst· 2022-05-17
Vision Transformer Adapter for Dense Predictions Code
#7OneFormer (DiNAT-L, single-scale)
48.4
PQst· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation Code
#8Visual Attention Network (VAN-B6 + Mask2Former)SOTA
48.2
PQst· 2022-02-20
Visual Attention Network Code
#9Mask2Former (single-scale)SOTA
48.1
PQst· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#10OneFormer (Swin-L, single-scale)
48
PQst· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation Code
#11Panoptic SegFormer (single-scale)SOTA
46.9
PQst· 2021-09-08
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers Code
#12CMT-DeepLab (single-scale)
46.6
PQst· 2022-06-17
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation Code
#13MaskFormer (single-scale)SOTA
44
PQst· 2021-07-13
Per-Pixel Classification is Not All You Need for Semantic Segmentation Code
#14Panoptic SegFormer (ResNet-101)
43.2
PQst· 2021-09-08
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers Code
#15MaX-DeepLab-L (single-scale)SOTA
42.2
PQst· 2020-12-01
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers Code
#16PanopticFPN+ResNeSt(single-scale)SOTA
37
PQst· 2020-04-19
ResNeSt: Split-Attention Networks Code
#17DETR-R101 (ResNet-101)
37
PQst· 2020-05-26
End-to-End Object Detection with Transformers Code
#18Axial-DeepLab-L(multi-scale)SOTA
36.8
PQst· 2020-03-17
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation Code
#19Panoptic FCN* (ResNet-50-FPN)
35.6
PQst· 2020-12-01
Fully Convolutional Networks for Panoptic Segmentation Code
#20Axial-DeepLab-L (single-scale)
35.6
PQst· 2020-03-17
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation Code
#21PanopticFPN++
33.6
PQst· 2020-05-26
End-to-End Object Detection with Transformers Code