HyperAI초신경

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

한국어

HyperAI초신경

Universal Domain Adaptation On Office 31

평가 지표

H-score

Source-Free

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	H-score	Source-Free	Paper Title	Repository
GATE	87.6	no	Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation	-
OVANet	86.5	no	OVANet: One-vs-All Network for Universal Domain Adaptation
LEAD	87.8	yes	LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
GLC	87.8	yes	Upcycling Models under Domain and Category Shift
UniAM	95.95	no	Universal Domain Adaptation via Compressive Attention Matching	-
SAN	91.8	no	Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier
DCC	80.16	no	Domain Consensus Clustering for Universal Domain Adaptation
CMU	73.14	no	Learning to Detect Open Classes for Universal Domain Adaptation
UAN	63.46	no	Universal Domain Adaptation	-
UniOT	91.13	no	Unified Optimal Transport Framework for Universal Domain Adaptation
UMAD	87.0	yes	UMAD: Universal Model Adaptation under Domain and Category Shift	-
MLNet	92.8	no	MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

0 of 12 row(s) selected.