Semantic Segmentation On Dark Zurich

Métriques

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
Refign (HRDA)	63.9	Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
CoDA	61.2	CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning
MIC	60.2	MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
Refign (DAFormer)	56.2	Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
HRDA	55.9	HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
SePiCo	54.2	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
DAFormer	53.8	DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
GPS-GLASS	46.4	GPS-GLASS: Learning Nighttime Semantic Segmentation Using Daytime Video and GPS data
SePiCo (DeepLab v2 ResNet-101)	45.4	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
DANNet (DeepLab v2 ResNet-101)	42.5	DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
MGCDA	42.5	Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
GCMA	42.0	Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
DANNet	36.76	DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
CIConv	34.5	Zero-Shot Day-Night Domain Adaptation with a Physics Prior

0 of 14 row(s) selected.

Semantic Segmentation On Dark Zurich | SOTA | HyperAI