HyperAI超神经

首页资讯最新论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Universal Domain Adaptation On Visda2017

评估指标

H-score

Source-free

评测结果

各个模型在此基准测试上的表现结果

模型名称	H-score	Source-free	Paper Title	Repository
OVANet	53.1	no	OVANet: One-vs-All Network for Universal Domain Adaptation
SAN	60.1	no	Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier
SHOT-O	44.0	yes	Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
DCC	43.0	no	Domain Consensus Clustering for Universal Domain Adaptation
LEAD	76.6	yes	LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
MLNet	69.9	no	MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation
UniAM	65.18	no	Universal Domain Adaptation via Compressive Attention Matching	-
UMAD	58.3	yes	UMAD: Universal Model Adaptation under Domain and Category Shift	-
GATE	56.4	no	Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation	-
UniOT	57.32	no	Unified Optimal Transport Framework for Universal Domain Adaptation
GLC	73.1	yes	Upcycling Models under Domain and Category Shift
UAN	34.8	no	Universal Domain Adaptation	-
TASC	90.36	no	Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation

0 of 13 row(s) selected.