Semantic Segmentation on ADE20K

Metric: Test Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Test Score▼	Extra Data	Paper	Date↕	Code
1	Swin-L (UperNet, ImageNet-22k pretrain)	62.8	No	Swin Transformer: Hierarchical Vision Transforme...	2021-03-25	Code
2	PyConvSegNet-152	56.52	No	Pyramidal Convolution: Rethinking Convolutional ...	2020-06-20	Code
3	LaU-offset-loss	56.41	No	Location-aware Upsampling for Semantic Segmentat...	2019-11-13	Code
4	LaU-regression-loss	56.32	No	Location-aware Upsampling for Semantic Segmentat...	2019-11-13	Code
5	EncNet + JPU	55.84	No	FastFCN: Rethinking Dilated Convolution in the B...	2019-03-28	Code
6	EncNet	55.67	No	Context Encoding for Semantic Segmentation	2018-03-23	Code
7	PSPNet	55.38	No	Pyramid Scene Parsing Network	2016-12-04	Code

#1Swin-L (UperNet, ImageNet-22k pretrain)SOTA
62.8
Test Score· 2021-03-25
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Code
#2PyConvSegNet-152SOTA
56.52
Test Score· 2020-06-20
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition Code
#3LaU-offset-lossSOTA
56.41
Test Score· 2019-11-13
Location-aware Upsampling for Semantic Segmentation Code
#4LaU-regression-loss
56.32
Test Score· 2019-11-13
Location-aware Upsampling for Semantic Segmentation Code
#5EncNet + JPUSOTA
55.84
Test Score· 2019-03-28
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation Code
#6EncNetSOTA
55.67
Test Score· 2018-03-23
Context Encoding for Semantic Segmentation Code
#7PSPNetSOTA
55.38
Test Score· 2016-12-04
Pyramid Scene Parsing Network Code