Synthetic To Real Translation On Synthia To 1

评估指标

MIoU (13 classes)

MIoU (16 classes)

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
DCF	75.9	69.3	Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation
HRDA+PiPa	74.8	68.2	PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
MIC	74.0	67.3	MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
HRDA	72.4	65.8	HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
SePiCo	71.4	64.3	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
CAMix (w DAFormer)	69.2	-	Context-Aware Mixup for Domain Adaptive Semantic Segmentation
EHTDI*	69.2	61.3	Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation
DAFormer	67.4	60.9	DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
SePiCo (ResNet-101)	66.5	58.1	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
TransDA-B	66.3	59.3	Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
EHTDI	64.6	57.8	Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation
G2L	64.4	56.8	G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation	-
ProDA+CRA	63.7	56.9	Cross-Region Domain Adaptation for Class-level Alignment	-
CorDA(ResNet-101)	62.8	55.0	Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
ProDA(ResNet-101)	62.0	55.5	Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
DSP(ResNet-101)	59.9	51.0	DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
CAMix (ResNet 101)	59.7	-	Context-Aware Mixup for Domain Adaptive Semantic Segmentation
SAC(ResNet-101)	59.3	52.6	Self-supervised Augmentation Consistency for Adapting Semantic Segmentation
CLST(ResNet-101)	57.8	49.8	Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation	-
Uncertainty + Adaboost (ResNet-101)	57.5	50.4	Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation

0 of 36 row(s) selected.