HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Domain Adaptation On Cityscapes To Acdc

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	Paper Title	Repository
DACS (DeepLabv2)	41.2	DACS: Domain Adaptation via Cross-domain Mixed Sampling
Refign (DAFormer)	65.5	Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
DAFormer	55.4	DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
VBLC (DeepLabv2)	47.8	VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
MIC	70.4	MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
CMFormer	60.1	Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation
Refign (HRDA)	72.1	Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
SoRA	78.8	SoRA: Singular Value Decomposed Low-Rank Adaptation for Domain Generalizable Representation Learning
DANNet	50.0	DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
FDA (DeepLabv2)	45.7	FDA: Fourier Domain Adaptation for Semantic Segmentation
VBLC (DAFormer)	64.2	VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
HRDA	68.0	HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
Rein	77.6	Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
MGCDA	48.7	Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
CoDA	72.6	CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning
HALO	71.9	Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

0 of 16 row(s) selected.