Domain Adaptation On Synthia To Cityscapes

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
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

평가 지표

평가 결과