Domain Adaptation On Synthia To Cityscapes

Metrics

mIoU

Results

Performance results of various models on this benchmark

		Paper Title	Repository
HALO	78.1	Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
ILM-ASSL	76.6	Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation
DCF	69.3	Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation
HRDA+PiPa	68.2	PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
MIC	67.3	MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
FREDOM - Transformer	67	FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
HRDA	65.8	HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
SePiCo	64.3	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
MIC + Guidance Training	63.8	Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation
DAFormer + ProCST	61.6	ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
DAFormer	60.9	DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
GtA-SFDA (DeepLabv2-ResNet101)	60.1	Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
FREDOM - DeepLabV2	59.1	FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
SePiCo (DeepLabv2-ResNet-101)	58.1	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
ProDA+CRA	56.9	Cross-Region Domain Adaptation for Class-level Alignment	-
CorDA (ResNet-101)	55.0	Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
SAC (ResNet-101)	52.6	Self-supervised Augmentation Consistency for Adapting Semantic Segmentation
STPL	51.8	Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation
RPT (ResNet-101)	51.2	Transferring and Regularizing Prediction for Semantic Segmentation	-
IAST (ResNet-101)	49.8	Instance Adaptive Self-Training for Unsupervised Domain Adaptation

0 of 33 row(s) selected.

Command Palette

Domain Adaptation On Synthia To Cityscapes

Metrics

Results