Domain Translation via Latent Space Mapping
This work addresses the problem of domain translation with limited supervision for researchers in computer vision and medical imaging, though it is incremental as it builds on existing manifold-based methods.
The paper tackles multi-domain translation by proposing Latent Space Mapping (LSM), a framework that learns latent spaces for each domain and regularizes them using dependencies between domain pairs, achieving competitive results on synthetic image translation, medical image segmentation, and facial landmark detection tasks.
In this paper, we investigate the problem of multi-domain translation: given an element $a$ of domain $A$, we would like to generate a corresponding $b$ sample in another domain $B$, and vice versa. Acquiring supervision in multiple domains can be a tedious task, also we propose to learn this translation from one domain to another when supervision is available as a pair $(a,b)\sim A\times B$ and leveraging possible unpaired data when only $a\sim A$ or only $b\sim B$ is available. We introduce a new unified framework called Latent Space Mapping (\model) that exploits the manifold assumption in order to learn, from each domain, a latent space. Unlike existing approaches, we propose to further regularize each latent space using available domains by learning each dependency between pairs of domains. We evaluate our approach in three tasks performing i) synthetic dataset with image translation, ii) real-world task of semantic segmentation for medical images, and iii) real-world task of facial landmark detection.