Domain-Symmetric Networks for Adversarial Domain Adaptation

Abstract

Unsupervised domain adaptation aims to learn a model of classifier for unlabeled samples on the target domain, given training data of labeled samples on the source domain. Impressive progress is made recently by learning invariant features via domain-adversarial training of deep networks. In spite of the recent progress, domain adaptation is still limited in achieving the invariance of feature distributions at a finer category level. To this end, we propose in this paper a new domain adaptation method called Domain-Symmetric Networks (SymNets). The proposed SymNet is based on a symmetric design of source and target task classifiers, based on which we also construct an additional classifier that shares with them its layer neurons. To train the SymNet, we propose a novel adversarial learning objective whose key design is based on a two-level domain confusion scheme, where the category-level confusion loss improves over the domain-level one by driving the learning of intermediate network features to be invariant at the corresponding categories of the two domains. Both domain discrimination and domain confusion are implemented based on the constructed additional classifier. Since target samples are unlabeled, we also propose a scheme of cross-domain training to help learn the target classifier. Careful ablation studies show the efficacy of our proposed method. In particular, based on commonly used base networks, our SymNets achieve the new state of the art on three benchmark domain adaptation datasets.

arXiv commentCVPR 2019 camera ready. Codes are available at: https://github.com/YBZh/SymNets

References in corpus (8)

• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• Domain-Adversarial Training of Neural Networks

Cited by in corpus (5)

• Domain Generalization Using a Mixture of Multiple Latent Domains
• Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation
• Unsupervised Domain Adaptation by Uncertain Feature Alignment
• Self-adaptive Re-weighted Adversarial Domain Adaptation
• Bi-Directional Generation for Unsupervised Domain Adaptation