Instance Segmentation on Cityscapes val

Metric: mask AP (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	mask AP▼	Extra Data	Paper	Date↕	Code
1	ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)	49	Yes	The Missing Point in Vision Transformers for Uni...	2025-05-26	Code
2	OneFormer (ConvNeXt-L, single-scale, Mapillary-Pretrained)	48.7	Yes	OneFormer: One Transformer to Rule Universal Ima...	2022-11-10	Code
3	OpenSeeD( SwinL, single-scale)	48.5	Yes	A Simple Framework for Open-Vocabulary Segmentat...	2023-03-14	Code
4	AFF-Base (single-scale, point-based Mask2Former)	46.2	No	AutoFocusFormer: Image Segmentation off the Grid	2023-04-24	Code
5	OneFormer (DiNAT-L, single-scale)	45.6	No	OneFormer: One Transformer to Rule Universal Ima...	2022-11-10	Code
6	OneFormer (Swin-L, single-scale)	45.6	No	OneFormer: One Transformer to Rule Universal Ima...	2022-11-10	Code
7	DiNAT-L (single-scale, Mask2Former)	45.1	No	Dilated Neighborhood Attention Transformer	2022-09-29	Code
8	AFF-Small (single-scale, point-based Mask2Former)	44	No	AutoFocusFormer: Image Segmentation off the Grid	2023-04-24	Code
9	Mask2Former (Swin-L, single-scale)	43.7	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
10	Mask2Former (Swin-B)	42	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
11	Mask2Former (Swin-S)	41.8	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
12	PolySnake	40.2	No	Recurrent Generic Contour-based Instance Segment...	2023-01-21	Code
13	Mask2Former (Swin-T)	39.7	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
14	Mask2Former (ResNet-101)	38.5	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
15	Mask2Former (ResNet-50)	37.4	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
16	GAIS-Net	37.1	Yes	Geometry-Aware Instance Segmentation with Dispar...	2020-06-14	Code
17	PointRend	35.8	No	PointRend: Image Segmentation as Rendering	2019-12-17	Code

#1ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)SOTA
49
mask AP· Extra Data· 2025-05-26
The Missing Point in Vision Transformers for Universal Image Segmentation Code
#2OneFormer (ConvNeXt-L, single-scale, Mapillary-Pretrained)SOTA
48.7
mask AP· Extra Data· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation Code
#3OpenSeeD( SwinL, single-scale)
48.5
mask AP· Extra Data· 2023-03-14
A Simple Framework for Open-Vocabulary Segmentation and Detection Code
#4AFF-Base (single-scale, point-based Mask2Former)
46.2
mask AP· 2023-04-24
AutoFocusFormer: Image Segmentation off the Grid Code
#5OneFormer (DiNAT-L, single-scale)
45.6
mask AP· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation Code
#6OneFormer (Swin-L, single-scale)
45.6
mask AP· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation Code
#7DiNAT-L (single-scale, Mask2Former)SOTA
45.1
mask AP· 2022-09-29
Dilated Neighborhood Attention Transformer Code
#8AFF-Small (single-scale, point-based Mask2Former)
44
mask AP· 2023-04-24
AutoFocusFormer: Image Segmentation off the Grid Code
#9Mask2Former (Swin-L, single-scale)SOTA
43.7
mask AP· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#10Mask2Former (Swin-B)
42
mask AP· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#11Mask2Former (Swin-S)
41.8
mask AP· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#12PolySnake
40.2
mask AP· 2023-01-21
Recurrent Generic Contour-based Instance Segmentation with Progressive Learning Code
#13Mask2Former (Swin-T)
39.7
mask AP· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#14Mask2Former (ResNet-101)
38.5
mask AP· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#15Mask2Former (ResNet-50)
37.4
mask AP· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#16GAIS-NetSOTA
37.1
mask AP· Extra Data· 2020-06-14
Geometry-Aware Instance Segmentation with Disparity Maps Code
#17PointRendSOTA
35.8
mask AP· 2019-12-17
PointRend: Image Segmentation as Rendering Code