Bi-Directional Generation for Unsupervised Domain Adaptation

Abstract

Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. The conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. To balance the mitigation of domain gap and the preservation of the inherent structure, we propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains. Specifically, two cross-domain generators are employed to synthesize one domain conditioned on the other. The performance of our proposed method can be further enhanced by the consistent classifiers and the cross-domain alignment constraints. We also design two classifiers which are jointly optimized to maximize the consistency on target sample prediction. Extensive experiments verify that our proposed model outperforms the state-of-the-art on standard cross domain visual benchmarks.

9 pages, 4 figures

References in corpus (11)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Adversarial Discriminative Domain Adaptation
• Learning Disentangled Semantic Representation for Domain Adaptation
• Contrastive Adaptation Network for Unsupervised Domain Adaptation
• Multi-Adversarial Domain Adaptation
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
• Fully Convolutional Adaptation Networks for Semantic Segmentation
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• Domain-Symmetric Networks for Adversarial Domain Adaptation
• Attending to Discriminative Certainty for Domain Adaptation