List your company
ResearchFormerly WizWand

Semi-supervised Domain Adaptation on Cityscapes GTA5 to Cityscapes (val)

65.6mIoUSemiSeg-Contrastive
53.74456.82259.962.978Apr 27, 2021
Updated 8mo ago

Evaluation results

MethodLinks
SemiSeg-ContrastiveLabeled Ratio=1/3, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0465.6
Liu et al.Labeled Ratio=1/3, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0464.6
ASSLabeled Ratio=1/3, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0464.5
SemiSeg-ContrastiveLabeled Ratio=1/6, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0464.2
SemiSeg-ContrastiveLabeled Ratio=1/15, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0462
Liu et al.Labeled Ratio=1/6, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0460.4
ASSLabeled Ratio=1/6, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0460.2
SemiSeg-ContrastiveLabeled Ratio=1/30, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0459.9
Liu et al.Labeled Ratio=1/15, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0457
ASSLabeled Ratio=1/15, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0456
Liu et al.Labeled Ratio=1/30, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0455.2
ASSLabeled Ratio=1/30, Backbone=Deeplabv2 with ResNet-101, Training=ImageNet pre-trained, Domain Adaptation=with domain adaptation2021.0454.2