HyperAI超神经

首页算力平台文档资讯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 Office Home

评估指标

H-Score

Source-free

VLM

评测结果

各个模型在此基准测试上的表现结果

				Paper Title	Repository
TASC	89.44	no	yes	Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation	-
UniAM	81.68	no	no	Universal Domain Adaptation via Compressive Attention Matching	-
MLNet	77.4	no	no	MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation
UniOT	76.57	no	no	Unified Optimal Transport Framework for Universal Domain Adaptation
SAN	75.9	no	no	Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier	-
GATE	75.6	no	no	Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation	-
GLC	75.6	yes	no	Upcycling Models under Domain and Category Shift
LEAD	75.0	yes	no	LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
OVANet	71.8	no	no	OVANet: One-vs-All Network for Universal Domain Adaptation
DCC	70.18	no	no	Domain Consensus Clustering for Universal Domain Adaptation	-
UMAD	70.1	yes	no	UMAD: Universal Model Adaptation under Domain and Category Shift	-
CMU	61.60	no	no	Learning to Detect Open Classes for Universal Domain Adaptation	-
UAN	56.58	no	no	Universal Domain Adaptation	-
SHOT-O	40.7	yes	no	Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation

0 of 14 row(s) selected.

Universal Domain Adaptation On Office Home | SOTA | HyperAI超神经