Zero-shot unsupervised image-to-image translation via exploiting semantic attributes

Recent studies have shown remarkable success in unsupervised image-to-image translation. However, if there is no access to enough images in target classes, learning a mapping from source classes to the target classes always suffers from mode collapse, especially the zero shot case, which limits the application of the existing methods. In this work, we propose a zero-shot unsupervised image-to-image translation framework to address this limita-tion, by effectively associating categories with their side information like attributes. To generalize the translator to previously unseen classes, we introduce two strategies for exploiting the semantic attribute space. First, we propose to preserve semantic relations to the visual space for effective guidance on where to map the input image. Second, expanding attribute space is introduced by utilizing attribute vectors of unseen classes, which al-leviates the mapping bias for unseen classes. Both of these strategies encourage the translator to explore the modes of unseen classes. Quantitative and qualitative results on different datasets validate the effectiveness of our proposed approach. Moreover, we demonstrate that our framework can be applied to fashion design task. (c) 2022 Elsevier B.V. All rights reserved.