Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective
Source-free Domain Adaptation (SFDA) is an emerging and challenging research area that addresses the problem of unsupervised domain adaptation (UDA) without source data. Though numerous successful methods have been proposed for SFDA a theoretical understanding of why these methods work well is still absent. In this paper we shed light on the theoretical perspective of existing SFDA methods. Specifically we find that SFDA loss functions comprising discriminability and diversity losses work in the same way as the training objective in the theory of self-training based on the expansion assumption which shows the existence of the target error bound. This finding brings two novel insights that enable us to build an improved SFDA method comprising 1) Model Training with Auto-Adjusting Diversity Constraint and 2) Augmentation Training with Teacher-Student Framework yielding a better recognition performance. Extensive experiments on three benchmark datasets demonstrate the validity of the theoretical analysis and our method.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityDomain AdaptationSource-Free Domain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety
Domain adaptation addresses the challenge where the distribution of target inference data differs from that of the source training data. Recently, data privacy has become a significant constraint, limiting access to …
Domain AdaptationSource-Free Domain AdaptationOn Deep Domain Adaptation: Some Theoretical Understandings
Compared with shallow domain adaptation, recent progress in deep domain adaptation has shown that it can achieve higher predictive performance and stronger capacity to tackle structural data (e.g., image and sequential d…
Domain AdaptationTransfer LearningVariational Model Perturbation for Source-Free Domain Adaptation
We aim for source-free domain adaptation, where the task is to deploy a model pre-trained on source domains to target domains. The challenges stem from the distribution shift from the source to the target domain, coupled…
Bayesian InferenceDomain AdaptationmodelSource-Free Domain AdaptationGeneralize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable fo…
Domain AdaptationDomain GeneralizationPseudo LabelSemantic Segmentation+2SFDLA: Source-Free Document Layout Analysis
Document Layout Analysis (DLA) is a fundamental task in document understanding. However, existing DLA and adaptation methods often require access to large-scale source data and target labels. This requirements severely l…
AvgDocument Layout Analysisdocument understanding