Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories

Abstract

Unsupervised domain adaptation (UDA) aims to learn the unlabeled target domain by transferring the knowledge of the labeled source domain. To date, most of the existing works focus on the scenario of one source domain and one target domain (1S1T), and just a few works concern the scenario of multiple source domains and one target domain (mS1T). While, to the best of our knowledge, almost no work concerns the scenario of one source domain and multiple target domains (1SmT), in which these unlabeled target domains may not necessarily share the same categories, therefore, contrasting to mS1T, 1SmT is more challenging. Accordingly, for such a new UDA scenario, we propose a UDA framework through the model parameter adaptation (PA-1SmT). A key ingredient of PA-1SmT is to transfer knowledge through adaptive learning of a common model parameter dictionary, which is completely different from existing popular methods for UDA, such as subspace alignment, distribution matching etc., and can also be directly used for DA of privacy protection due to the fact that the knowledge is transferred just via the model parameters rather than data itself. Finally, our experimental results on three domain adaptation benchmark datasets demonstrate the superiority of our framework.

References in corpus (8)

• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Adversarial Discriminative Domain Adaptation
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• Transfer Prototype-based Fuzzy Clustering
• Deep Transfer Learning with Joint Adaptation Networks
• Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
• Correlation Alignment by Riemannian Metric for Domain Adaptation

Cited by in corpus (12)

• Recent Advances in Open Set Recognition: A Survey
• DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Multi-Target Domain Adaptation with Collaborative Consistency Learning
• Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
• Federated Multi-Target Domain Adaptation
• Universal Person Re-Identification
• Open Compound Domain Adaptation
• Additive Adversarial Learning for Unbiased Authentication
• Mixed Set Domain Adaptation
• Domain-Specific Bias Filtering for Single Labeled Domain Generalization
• Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously