Image To Image Translation On Synthia To

评估指标

mIoU (13 classes)

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
HRDA + PiPa	74.8	PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
MIC	74.0	MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
HRDA	72.4	HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
SePiCo	71.4	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
CAMix (w DAFormer)	69.2	Context-Aware Mixup for Domain Adaptive Semantic Segmentation
DAFormer + ProCST	68.2	ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
DAFormer	67.4	DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
TransDA-B	66.3	Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
CPSL	65.3	Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
ProDA+CRA	63.7	Cross-Region Domain Adaptation for Class-level Alignment	-
ProDA	62.0	Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
CAMix (w Deeplabv2 ResNet 101)	59.7	Context-Aware Mixup for Domain Adaptive Semantic Segmentation
IAST(ResNet-101)	57.0	Instance Adaptive Self-Training for Unsupervised Domain Adaptation
PyCDA (ResNet-101)	53.3	Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
FADA (ResNet-101)	52.5	Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
Bidirectional Learning (ResNet-101)	51.4	Bidirectional Learning for Domain Adaptation of Semantic Segmentation
DADA (ResNet-101)	49.8	DADA: Depth-aware Domain Adaptation in Semantic Segmentation
LRENT (DeepLabv2)	48.7	Confidence Regularized Self-Training
SWD	48.1	Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
ADVENT	48	ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

0 of 28 row(s) selected.