We present a novel and unified deep learning framework which is capable of domain-invariant representation from data across multiple domains. by adversarial training with additional ability to exploit-specific information, the proposed network is able to perform continuous-domain image translation and manipulation, and produces desirable output accordingly. In addition, the resulting feature representation exhibits performance of unsupervised domain adaptation, which also verifies the of the proposed model in learning disentangled features for cross-domain data.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2018) studied this question.