List your company
ResearchFormerly WizWand

Semantic Segmentation on Cityscapes fine (test)

81.9mIoUCCNet
59.43665.26871.176.932Aug 2, 2018Jan 13, 2019Jun 26, 2019Dec 7, 2019May 19, 2020Oct 30, 2020Apr 13, 2021
Updated 8mo ago

Evaluation results

MethodLinks
CCNetBackbone=ResNet-1012020.1281.9
SETR-PUPBackbone=T-Large, Training data annotation=fine and coarse2020.1281.64
DANetBackbone=ResNet-1012020.1281.5
SETR-PUPBackbone=T-Large, Training iterations=100k2020.1281.08
DenseASPPBackbone=DenseNet-1612020.1280.6
PSANetBackbone=ResNet-1012020.1280.1
OCNetBackbone=ResNet-1012020.1280.1
Axial-DeepLab-XLBackbone=Axial-ResNet-XL2020.1279.9
Axial-DeepLab-LBackbone=Axial-ResNet-L2020.1279.5
BiSeNetBaseModel=Res1012018.0878.9
BiSeNetBackbone=ResNet-1012020.1278.9
PSPNetBaseModel=Res1012018.0878.4
PSPNetBackbone=ResNet-1012020.1278.4
BiSeNetBaseModel=Res182018.0877.7
DUCBaseModel=Res1522018.0876.1
SwiftNetPretrained on ImageNet=true, Number of Parameters=11.8M, GFLOPs=104, Resolution=1024 x 20482021.0475.5
Lite-HRNet-30Pretrained on ImageNet=false, Number of Parameters=1.8M, GFLOPs=3.02, Resolution=512 x 10242021.0475.3
BiSeNetV1 BPretrained on ImageNet=true, Number of Parameters=49.0M, GFLOPs=55.3, Resolution=768 x 15362021.0474.7
RefineNetBaseModel=Res1012018.0873.6
Lite-HRNet-18Pretrained on ImageNet=false, Number of Parameters=1.1M, GFLOPs=1.95, Resolution=512 x 10242021.0472.8
MobileNetV3Backbone=V3, OS=16, MAdds (f)=9.74B, MAdds (h)=2.48B, CPU (f)=2.47s, CPU (h)=657ms2019.0572.6
BiSeNetV2 SmallPretrained on ImageNet=false, GFLOPs=21.15, Resolution=512 x 10242021.0472.6
MobileNetV3Pretrained on ImageNet=true, Number of Parameters=1.5M, GFLOPs=9.1, Resolution=1024 x 20482021.0472.6
MobileNetV3Backbone=V3, OS=32, MAdds (f)=7.74B, MAdds (h)=1.98B, CPU (f)=2.06s, CPU (h)=534ms2019.0572
FasterSegPretrained on ImageNet=true, Number of Parameters=4.4M, GFLOPs=28.2, Resolution=1024 x 20482021.0471.5
BiSeNetBaseModel=Xception392018.0871.4
DF1-Seg-d8Pretrained on ImageNet=true, Resolution=1024 x 20482021.0471.4
CASPretrained on ImageNet=true, Resolution=768 x 15362021.0470.5
DeepLab-v2+CRFBaseModel=Res1012018.0870.4
DFANet A'Pretrained on ImageNet=true, Number of Parameters=7.8M, GFLOPs=1.7, Resolution=512 x 10242021.0470.3
LRRBaseModel=VGG162018.0869.7
ICNetPretrained on ImageNet=true, GFLOPs=28.3, Resolution=1024 x 20482021.0469.5
MobileNetV3-SmallBackbone=V3-Small, OS=16, MAdds (f)=2.90B, MAdds (h)=0.74B, CPU (f)=1.21s, CPU (h)=327ms2019.0569.4
MobileNet V3-SmallPretrained on ImageNet=true, Number of Parameters=0.5M, GFLOPs=2.7, Resolution=512 x 10242021.0469.4
BiSeNetV1 APretrained on ImageNet=true, Number of Parameters=5.8M, GFLOPs=14.8, Resolution=768 x 15362021.0468.4
MobileNetV3-SmallBackbone=V3-Small, OS=32, MAdds (f)=2.06B, MAdds (h)=0.53B, CPU (f)=1.03s, CPU (h)=275ms2019.0568.3
Fast-SCNNPretrained on ImageNet=false, Resolution=1024 x 20482021.0468
Dilation10BaseModel=VGG162018.0867.1
AdelaideBaseModel=VGG162018.0866.4
ESPNetv2MAdds (h)=2.7B2019.0566.2
FCN-8sBaseModel=VGG162018.0865.3
DeepLabBaseModel=VGG162018.0863.1
CCC2MAdds (h)=3.15B2019.0562
ESPNetv1MAdds (h)=4.5B2019.0560.3