Multi-Adversarial Domain Adaptation

Abstract

Recent advances in deep domain adaptation reveal that adversarial learning can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target domains. Existing domain adversarial adaptation methods based on single domain discriminator only align the source and target data distributions without exploiting the complex multimode structures. In this paper, we present a multi-adversarial domain adaptation (MADA) approach, which captures multimode structures to enable fine-grained alignment of different data distributions based on multiple domain discriminators. The adaptation can be achieved by stochastic gradient descent with the gradients computed by back-propagation in linear-time. Empirical evidence demonstrates that the proposed model outperforms state of the art methods on standard domain adaptation datasets.

AAAI 2018 Oral. arXiv admin note: substantial text overlap with arXiv:1705.10667, arXiv:1707.07901

References in corpus (8)

• Conditional Generative Adversarial Nets
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Domain Separation Networks
• Unrolled Generative Adversarial Networks
• Generative Multi-Adversarial Networks

Cited by in corpus (14)

• Multi-Representation Adaptation Network for Cross-domain Image Classification
• A Survey of Domain Adaptation for Neural Machine Translation
• On Learning Invariant Representation for Domain Adaptation
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
• Domain Alignment with Triplets
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
• Aggregating From Multiple Target-Shifted Sources
• Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
• Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy
• Domain Conditioned Adaptation Network
• Bi-Directional Generation for Unsupervised Domain Adaptation
• Event-Related Bias Removal for Real-time Disaster Events
• Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation
• How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?