HyperAI초신경

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

한국어

HyperAI초신경

Universal Domain Adaptation On Domainnet

평가 지표

H-Score

Source-free

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	H-Score	Source-free	Paper Title	Repository
GLC	55.1	yes	Upcycling Models under Domain and Category Shift
UMAD	47.1	yes	UMAD: Universal Model Adaptation under Domain and Category Shift	-
UAN	40.98	no	Universal Domain Adaptation	-
UniAM	61.52	no	Universal Domain Adaptation via Compressive Attention Matching	-
CMU	48.25	no	Learning to Detect Open Classes for Universal Domain Adaptation
TASC	73.28	no	Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation
OVANet	50.7	no	OVANet: One-vs-All Network for Universal Domain Adaptation
SAN	52.0	no	Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier
LEAD	50.8	yes	LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
UniOT	52.04	no	Unified Optimal Transport Framework for Universal Domain Adaptation
SHOT-O	32.6	no	Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
DCC	49.20	no	Domain Consensus Clustering for Universal Domain Adaptation

0 of 12 row(s) selected.