List your company
ResearchFormerly WizWand

Semantic Segmentation on Cityscapes fine (val)

80.3mIoUBiSeNet
64.768.7572.876.85Aug 2, 2018Mar 22, 2019Nov 10, 2019Jun 30, 2020Feb 18, 2021Oct 9, 2021May 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
BiSeNetBaseModel=Res1012018.0880.3
BiSeNetBaseModel=Res182018.0878.6
DUCBaseModel=Res1522018.0876.7
SlotConEpochs=800, Multi crop=false, Obj. Prior=false2022.0576.2
DetConEpochs=1000, Multi crop=false, Obj. Prior=true2022.0576.1
Lite-HRNet-30Pretrained on ImageNet=false, Number of Parameters=1.8M, GFLOPs=3.02, Resolution=512 x 10242021.0476
PC2SegBackbone=ResNet-101, Base Architecture=DeepLab-v3+2021.0875.99
DenseCLEpochs=800, Multi crop=false, Obj. Prior=false2022.0575.8
ORLEpochs=800, Multi crop=true, Obj. Prior=true2022.0575.6
MobileNextPretrained on ImageNet=true, Number of Parameters=4.5M, GFLOPs=10.1*, Resolution=1024 x 20482021.0475.5
SwiftNetPretrained on ImageNet=true, Number of Parameters=11.8M, GFLOPs=104, Resolution=1024 x 20482021.0475.4
PC2SegBackbone=ResNet-50, Base Architecture=DeepLab-v3+2021.0875.39
Revisit.Epochs=800, Multi crop=true, Obj. Prior=false2022.0575.3
PixProEpochs=800, Multi crop=false, Obj. Prior=false2022.0575.2
RELICv2Pre-training=ImageNet, Fine-tuning=true, Fine-tuning epochs=1602022.0175.2
Sup. baselineBackbone=ResNet-101, Base Architecture=DeepLab-v3+2021.0874.88
BiSeNetV1 BPretrained on ImageNet=true, Number of Parameters=49.0M, GFLOPs=55.3, Resolution=768 x 15362021.0474.8
ShelfNetPretrained on ImageNet=true, Number of Parameters=36.9M, GFLOPs=46.8, Resolution=1024 x 20482021.0474.8
BYOLPre-training=ImageNet, Fine-tuning=true, Fine-tuning epochs=1602022.0174.6
Lite-HRNet-18Pretrained on ImageNet=false, Number of Parameters=1.1M, GFLOPs=1.95, Resolution=512 x 10242021.0473.8
MoCo v2Epochs=800, Multi crop=false, Obj. Prior=false2022.0573.8
Sup. baselineBackbone=ResNet-50, Base Architecture=DeepLab-v3+2021.0873.64
BiSeNetV2 SmallPretrained on ImageNet=false, GFLOPs=21.15, Resolution=512 x 10242021.0473.4
FasterSegPretrained on ImageNet=true, Number of Parameters=4.4M, GFLOPs=28.2, Resolution=1024 x 20482021.0473.1
DF1-Seg-d8Pretrained on ImageNet=true, Resolution=1024 x 20482021.0472.4
MobileNetV3Pretrained on ImageNet=true, Number of Parameters=1.5M, GFLOPs=9.1, Resolution=1024 x 20482021.0472.4
BiSeNetBaseModel=Xception392018.0872
GASPretrained on ImageNet=true, Resolution=769 x 15372021.0471.8
CASPretrained on ImageNet=true, Resolution=768 x 15362021.0471.6
DeepLab-v2+CRFBaseModel=Res1012018.0871.4
SwiftNetPretrained on ImageNet=true, Number of Parameters=11.8M, GFLOPs=26, Resolution=512 x 10242021.0470.2
LRRBaseModel=VGG162018.0870
BiSeNetV1 APretrained on ImageNet=true, Number of Parameters=5.8M, GFLOPs=14.8, Resolution=768 x 15362021.0469
Dilation10BaseModel=VGG162018.0868.7
Fast-SCNNPretrained on ImageNet=false, Resolution=1024 x 20482021.0468.6
MobileNet V2 0.5Pretrained on ImageNet=true, Number of Parameters=0.3M, GFLOPs=3.73, Resolution=512 x 10242021.0468.6
HRNet-W16Pretrained on ImageNet=true, Number of Parameters=2.0M, GFLOPs=7.8, Resolution=512 x 10242021.0468.6
MobileNet V3-SmallPretrained on ImageNet=true, Number of Parameters=0.5M, GFLOPs=2.7, Resolution=512 x 10242021.0468.4
DMTBackbone=ResNet-101, Base Architecture=DeepLab-v22021.0868.16
ICNetPretrained on ImageNet=true, GFLOPs=28.3, Resolution=1024 x 20482021.0467.7
sGANBackbone=ResNet-101, Base Architecture=DeepLab-v22021.0865.8
random init.Multi crop=false, Obj. Prior=false2022.0565.3