Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Panoptic Segmentation
/
Cityscapes val
Panoptic Segmentation on Cityscapes val
Metric: mIoU (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Hide extra data
Export CSV
Sort:
mIoU (best first)
mIoU (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
mIoU
▼
Extra Data
Paper
Date
↕
Code
1
EfficientPS (Cityscapes-fine)
90.3
No
EfficientPS: Efficient Panoptic Segmentation
2020-04-05
Code
2
ViT-P (OneFormer, InternImage-H)
85.4
No
The Missing Point in Vision Transformers for Uni...
2025-05-26
Code
3
Panoptic-DeepLab (SWideRNet [1, 1, 4.5], Mapillary Vistas, multi-scale)
85.3
Yes
Scaling Wide Residual Networks for Panoptic Segm...
2020-11-23
-
4
OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)
84.6
Yes
OneFormer: One Transformer to Rule Universal Ima...
2022-11-10
Code
5
Axial-DeepLab-XL (Mapillary Vistas, multi-scale)
84.6
Yes
Axial-DeepLab: Stand-Alone Axial-Attention for P...
2020-03-17
Code
6
Panoptic-DeepLab (SWideRNet [1, 1, 4.5], Mapillary Vistas, single-scale)
84.6
Yes
Scaling Wide Residual Networks for Panoptic Segm...
2020-11-23
-
7
OneFormer (ConvNeXt-XL, single-scale)
83.6
No
OneFormer: One Transformer to Rule Universal Ima...
2022-11-10
Code
8
kMaX-DeepLab (single-scale)
83.5
No
kMaX-DeepLab: k-means Mask Transformer
2022-07-08
Code
9
DiNAT-L (Mask2Former)
83.4
No
Dilated Neighborhood Attention Transformer
2022-09-29
Code
10
OneFormer (DiNAT-L, single-scale)
83.1
No
OneFormer: One Transformer to Rule Universal Ima...
2022-11-10
Code
11
OneFormer (ConvNeXt-L, single-scale)
83
No
OneFormer: One Transformer to Rule Universal Ima...
2022-11-10
Code
12
AFF-Base (single-scale, point-based Mask2Former)
83
No
AutoFocusFormer: Image Segmentation off the Grid
2023-04-24
Code
13
OneFormer (Swin-L, single-scale)
83
No
OneFormer: One Transformer to Rule Universal Ima...
2022-11-10
Code
14
Mask2Former (Swin-L)
82.9
No
Masked-attention Mask Transformer for Universal ...
2021-12-02
Code
15
AFF-Small (single-scale, point-based Mask2Former)
82.2
No
AutoFocusFormer: Image Segmentation off the Grid
2023-04-24
Code
16
EfficientPS
82.1
Yes
EfficientPS: Efficient Panoptic Segmentation
2020-04-05
Code
17
Panoptic-DeepLab (X71)
81.5
Yes
Panoptic-DeepLab: A Simple, Strong, and Fast Bas...
2019-11-22
Code
18
CMT-DeepLab (MaX-S, single-scale, IN-1K)
81.4
No
CMT-DeepLab: Clustering Mask Transformers for Pa...
2022-06-17
Code
19
Dynamically Instantiated Network (ResNet-101)
79.8
No
Weakly- and Semi-Supervised Panoptic Segmentation
2018-08-10
Code
20
COPS (ResNet-50)
79.3
No
Combinatorial Optimization for Panoptic Segmenta...
2021-06-06
Code
21
AdaptIS (ResNeXt-101)
79.2
No
AdaptIS: Adaptive Instance Selection Network
2019-09-17
-
22
UPSNet (ResNet-101, multiscale)
79.2
Yes
UPSNet: A Unified Panoptic Segmentation Network
2019-01-12
Code
23
TASCNet (ResNet-50, multi-scale)
78
Yes
Learning to Fuse Things and Stuff
2018-12-04
-
24
UPSNet (ResNet-101)
77.8
Yes
UPSNet: A Unified Panoptic Segmentation Network
2019-01-12
Code
25
TASCNet (ResNet-50)
77.8
Yes
Learning to Fuse Things and Stuff
2018-12-04
-
26
AdaptIS (ResNet-101)
77.2
No
AdaptIS: Adaptive Instance Selection Network
2019-09-17
-
27
Panoptic FPN (ResNet-101)
75.7
No
Panoptic Feature Pyramid Networks
2019-01-08
Code
28
AUNet (ResNet-101-FPN)
75.6
No
Attention-guided Unified Network for Panoptic Se...
2018-12-10
-
29
AdaptIS (ResNet-50)
75.3
No
AdaptIS: Adaptive Instance Selection Network
2019-09-17
-
30
UPSNet (ResNet-50)
75.2
No
UPSNet: A Unified Panoptic Segmentation Network
2019-01-12
Code
#1
EfficientPS (Cityscapes-fine)
SOTA
90.3
mIoU
· 2020-04-05
EfficientPS: Efficient Panoptic Segmentation
Code
#2
ViT-P (OneFormer, InternImage-H)
85.4
mIoU
· 2025-05-26
The Missing Point in Vision Transformers for Universal Image Segmentation
Code
#3
Panoptic-DeepLab (SWideRNet [1, 1, 4.5], Mapillary Vistas, multi-scale)
85.3
mIoU
· Extra Data
· 2020-11-23
Scaling Wide Residual Networks for Panoptic Segmentation
#4
OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)
84.6
mIoU
· Extra Data
· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation
Code
#5
Axial-DeepLab-XL (Mapillary Vistas, multi-scale)
SOTA
84.6
mIoU
· Extra Data
· 2020-03-17
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
Code
#6
Panoptic-DeepLab (SWideRNet [1, 1, 4.5], Mapillary Vistas, single-scale)
84.6
mIoU
· Extra Data
· 2020-11-23
Scaling Wide Residual Networks for Panoptic Segmentation
#7
OneFormer (ConvNeXt-XL, single-scale)
83.6
mIoU
· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation
Code
#8
kMaX-DeepLab (single-scale)
83.5
mIoU
· 2022-07-08
kMaX-DeepLab: k-means Mask Transformer
Code
#9
DiNAT-L (Mask2Former)
83.4
mIoU
· 2022-09-29
Dilated Neighborhood Attention Transformer
Code
#10
OneFormer (DiNAT-L, single-scale)
83.1
mIoU
· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation
Code
#11
OneFormer (ConvNeXt-L, single-scale)
83
mIoU
· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation
Code
#12
AFF-Base (single-scale, point-based Mask2Former)
83
mIoU
· 2023-04-24
AutoFocusFormer: Image Segmentation off the Grid
Code
#13
OneFormer (Swin-L, single-scale)
83
mIoU
· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation
Code
#14
Mask2Former (Swin-L)
82.9
mIoU
· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation
Code
#15
AFF-Small (single-scale, point-based Mask2Former)
82.2
mIoU
· 2023-04-24
AutoFocusFormer: Image Segmentation off the Grid
Code
#16
EfficientPS
82.1
mIoU
· Extra Data
· 2020-04-05
EfficientPS: Efficient Panoptic Segmentation
Code
#17
Panoptic-DeepLab (X71)
SOTA
81.5
mIoU
· Extra Data
· 2019-11-22
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
Code
#18
CMT-DeepLab (MaX-S, single-scale, IN-1K)
81.4
mIoU
· 2022-06-17
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
Code
#19
Dynamically Instantiated Network (ResNet-101)
SOTA
79.8
mIoU
· 2018-08-10
Weakly- and Semi-Supervised Panoptic Segmentation
Code
#20
COPS (ResNet-50)
79.3
mIoU
· 2021-06-06
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach
Code
#21
AdaptIS (ResNeXt-101)
79.2
mIoU
· 2019-09-17
AdaptIS: Adaptive Instance Selection Network
#22
UPSNet (ResNet-101, multiscale)
79.2
mIoU
· Extra Data
· 2019-01-12
UPSNet: A Unified Panoptic Segmentation Network
Code
#23
TASCNet (ResNet-50, multi-scale)
78
mIoU
· Extra Data
· 2018-12-04
Learning to Fuse Things and Stuff
#24
UPSNet (ResNet-101)
77.8
mIoU
· Extra Data
· 2019-01-12
UPSNet: A Unified Panoptic Segmentation Network
Code
#25
TASCNet (ResNet-50)
77.8
mIoU
· Extra Data
· 2018-12-04
Learning to Fuse Things and Stuff
#26
AdaptIS (ResNet-101)
77.2
mIoU
· 2019-09-17
AdaptIS: Adaptive Instance Selection Network
#27
Panoptic FPN (ResNet-101)
75.7
mIoU
· 2019-01-08
Panoptic Feature Pyramid Networks
Code
#28
AUNet (ResNet-101-FPN)
75.6
mIoU
· 2018-12-10
Attention-guided Unified Network for Panoptic Segmentation
#29
AdaptIS (ResNet-50)
75.3
mIoU
· 2019-09-17
AdaptIS: Adaptive Instance Selection Network
#30
UPSNet (ResNet-50)
75.2
mIoU
· 2019-01-12
UPSNet: A Unified Panoptic Segmentation Network
Code