Cycle-consistent Conditional Adversarial Transfer Networks

Abstract

Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions. Recently, adversarial training have been successfully applied to domain adaptation and achieved state-of-the-art performance. However, there is still a fatal weakness existing in current adversarial models which is raised from the equilibrium challenge of adversarial training. Specifically, although most of existing methods are able to confuse the domain discriminator, they cannot guarantee that the source domain and target domain are sufficiently similar. In this paper, we propose a novel approach named {\it cycle-consistent conditional adversarial transfer networks} (3CATN) to handle this issue. Our approach takes care of the domain alignment by leveraging adversarial training. Specifically, we condition the adversarial networks with the cross-covariance of learned features and classifier predictions to capture the multimodal structures of data distributions. However, since the classifier predictions are not certainty information, a strong condition with the predictions is risky when the predictions are not accurate. We, therefore, further propose that the truly domain-invariant features should be able to be translated from one domain to the other. To this end, we introduce two feature translation losses and one cycle-consistent loss into the conditional adversarial domain adaptation networks. Extensive experiments on both classical and large-scale datasets verify that our model is able to outperform previous state-of-the-arts with significant improvements.

arXiv commentCodes at github.com/lijin118/3CATN

References in corpus (13)

• Conditional Generative Adversarial Nets
• 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
• VisDA: The Visual Domain Adaptation Challenge
• Unsupervised Cross-Domain Image Generation
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• Leveraging the Invariant Side of Generative Zero-Shot Learning
• Zero-Shot Learning -- The Good, the Bad and the Ugly
• Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
• From Zero-Shot Learning to Cold-Start Recommendation