Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning

摘要

Most recently proposed unsupervised domain adaptation algorithms attempt to learn domain invariant features by confusing a domain classifier through adversarial training. In this paper, we argue that this may not be an optimal solution in the real-world setting (a.k.a. in the wild) as the difference in terms of label information between domains has been largely ignored. As labeled instances are not available in the target domain in unsupervised domain adaptation tasks, it is difficult to explicitly capture the label difference between domains. To address this issue, we propose to learn a disentangled latent representation based on implicit autoencoders. In particular, a latent representation is disentangled into a global code and a local code. The global code is capturing category information via an encoder with a prior, and the local code is transferable across domains, which captures the “style” related information via an implicit decoder. Experimental results on digit recognition, object recognition and semantic segmentation demonstrate the effectiveness of our proposed method.