Image To Image Translation On Gtav To

Metrics

mIoU

Results

Performance results of various models on this benchmark

Model Name	mIoU	Paper Title	Repository
CPSL	60.8	Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
G2L	59.7	G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation	-
CAMix (w Deeplabv2 ResNet 101)	55.2	Context-Aware Mixup for Domain Adaptive Semantic Segmentation
CCM	49.9	Content-Consistent Matching for Domain Adaptive Semantic Segmentation
CAMix (w DAFormer)	70.0	Context-Aware Mixup for Domain Adaptive Semantic Segmentation
ADVENT	44.8	ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
DDB	62.7	Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation
CBST	47.0	Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
VGG16 60.3	41.3	Very Deep Convolutional Networks for Large-Scale Image Recognition
SePiCo	70.3	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation	-
ProDA+CRA	58.6	Cross-Region Domain Adaptation for Class-level Alignment	-
DAFormer + PiPa	71.7	PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
ResNet101 65.1	41.7	Deep Residual Learning for Image Recognition
DAFormer + ProCST	69.4	ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
EHTDI*	62.0	Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation
ProDA	57.5	Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
HRDA + PiPa	75.6	PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
Bidirectional Learning	41.3	Bidirectional Learning for Domain Adaptation of Semantic Segmentation
HRDA	73.8	HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
DAFormer	68.3	DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

0 of 22 row(s) selected.