A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
This work addresses the challenge of domain shift in image processing for applications like translation and adaptation, though it appears incremental as it builds on existing adversarial training methods.
The authors tackled the problem of learning domain-invariant representations from multi-domain image data, resulting in a framework that enables continuous cross-domain image translation and manipulation while achieving superior performance in unsupervised domain adaptation.
We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains. Realized by adversarial training with additional ability to exploit domain-specific information, the proposed network is able to perform continuous cross-domain image translation and manipulation, and produces desirable output images accordingly. In addition, the resulting feature representation exhibits superior performance of unsupervised domain adaptation, which also verifies the effectiveness of the proposed model in learning disentangled features for describing cross-domain data.