HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Semantic Segmentation On Nighttime Driving

Metrics

mIoU

Results

Performance results of various models on this benchmark

Model Name
mIoU
Paper TitleRepository
DANNet (RefineNet)42.36DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
Refign (DAFormer)56.8Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
DANNet (DeepLab-v2)44.98DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
TADP60.8Text-image Alignment for Diffusion-based Perception
CoDA59.2CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning
CIConv41.6Zero-Shot Day-Night Domain Adaptation with a Physics Prior
DMAda36.1Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime-
Refign (HRDA)58.0Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
ERF-PSPNet45.09See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion-
MGCDA49.4Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
GCMA45.6Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
DANNet (PSPNet)47.70DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
0 of 12 row(s) selected.
Semantic Segmentation On Nighttime Driving | SOTA | HyperAI