Unsupervised Domain Adaptation By Optimal Transportation Of Clusters Between Domains
Unsupervised domain adaptation (UDA) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain. Typically, to guarantee desirable knowledge transfer, aligning the distribution between source and target domain from a global perspective is widely adopted in UDA. Recent researchers further point out the importance of local-level alignment and borrow the experience from Optimal Transport (OT) theory to construct instance-pair alignment. However, existing OT-based algorithms are limited to resolve class imbalance challenge and require a huge computation cost when considering a large-scale training situation. In this paper, we address these two issues by proposing a Clustering-based Optimal Transport (COT) algorithm, which formulates the alignment procedure as an Optimal Transport problem by capturing the fine-grained attribute alignment. Concretely, COT innovatively designs the loss derived from discrete Kantorovich dual form to construct a mapping between clustering centers in source and target domain, which simultaneously eliminates the negative effect brought by class imbalance and reduces the computation cost on the basis of theoretical analysis. Finally, our COT together with some previous UDA methods achieve superior performance on several benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeClusteringDomain AdaptationTransfer LearningUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Variational Wasserstein Clustering
We propose a new clustering method based on optimal transportation. We solve optimal transportation with variational principles, and investigate the use of power diagrams as transportation plans for aggregating arbitrary…
ClusteringDomain AdaptationRepresentation LearningFeature Selection for Unsupervised Domain Adaptation using Optimal Transport
In this paper, we propose a new feature selection method for unsupervised domain adaptation based on the emerging optimal transportation theory. We build upon a recent theoretical analysis of optimal transport in domain …
Domain Adaptationfeature selectionUnsupervised Domain AdaptationOptimal Transport for Domain Adaptation
Domain adaptation from one data space (or domain) to another is one of the most challenging tasks of modern data analytics. If the adaptation is done correctly, models built on a specific data space become more robust wh…
Domain AdaptationInfoOT: Information Maximizing Optimal Transport
Optimal transport aligns samples across distributions by minimizing the transportation cost between them, e.g., the geometric distances. Yet, it ignores coherence structure in the data such as clusters, does not handle o…
Domain AdaptationRetrievalCluster Alignment with a Teacher for Unsupervised Domain Adaptation
Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. However, suc…
ClusteringDomain AdaptationUnsupervised Domain Adaptation