LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has emerged to achieve UniDA without access to source data, which tends to be more practical due to data protection policies. The main challenge lies in determining whether covariate-shifted samples belong to target-private unknown categories. Existing methods tackle this either through hand-crafted thresholding or by developing time-consuming iterative clustering strategies. In this paper, we propose a new idea of LEArning Decomposition (LEAD), which decouples features into source-known and -unknown components to identify target-private data. Technically, LEAD initially leverages the orthogonal decomposition analysis for feature decomposition. Then, LEAD builds instance-level decision boundaries to adaptively identify target-private data. Extensive experiments across various UniDA scenarios have demonstrated the effectiveness and superiority of LEAD. Notably, in the OPDA scenario on VisDA dataset, LEAD outperforms GLC by 3.5% overall H-score and reduces 75% time to derive pseudo-labeling decision boundaries. Besides, LEAD is also appealing in that it is complementary to most existing methods. The code is available at https://github.com/ispc-lab/LEAD.
Code (2)
Tasks
Domain AdaptationTransfer LearningUniversal Domain AdaptationSimilar Papers 제목 키워드 기반
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted …
ClusteringContrastive LearningDomain AdaptationSource-Free Domain Adaptation+1Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model
In practice, domain shifts are likely to occur between training and test data, necessitating domain adaptation (DA) to adjust the pre-trained source model to the target domain. Recently, universal domain adaptation (UniD…
Domain AdaptationOut-of-Distribution DetectionUniversal Domain AdaptationProbability Distribution Alignment and Low-Rank Weight Decomposition for Source-Free Domain Adaptive Brain Decoding
Brain decoding currently faces significant challenges in individual differences, modality alignment, and high-dimensional embeddings. To address individual differences, researchers often use source subject data, which le…
Brain DecodingDomain AdaptationImage ReconstructionSource-Free Domain AdaptationKnow the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Design
Single-agent LLMs hit hard limits--finite context, role overload, and brittle domain transfer. Conventional multi-agent fixes soften those edges yet expose fresh pains: ill-posed decompositions, fuzzy contracts, and veri…
COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation
Universal domain adaptation (UniDA) aims to address domain and category shifts across data sources. Recently, due to more stringent data restrictions, researchers have introduced source-free UniDA (SF-UniDA). SF-UniDA me…
Domain AdaptationFew-Shot LearningLanguage ModellingUniversal Domain Adaptation