DINO: A Conditional Energy-Based GAN for Domain Translation
This addresses the issue of semantic loss in domain translation for applications like cross-modal data processing, though it appears incremental as an improvement over existing GAN-based methods.
The paper tackles the problem of domain translation by proposing a conditional energy-based GAN framework that enforces preservation of shared semantics, performing well in challenging tasks like video-driven speech reconstruction.
Domain translation is the process of transforming data from one domain to another while preserving the common semantics. Some of the most popular domain translation systems are based on conditional generative adversarial networks, which use source domain data to drive the generator and as an input to the discriminator. However, this approach does not enforce the preservation of shared semantics since the conditional input can often be ignored by the discriminator. We propose an alternative method for conditioning and present a new framework, where two networks are simultaneously trained, in a supervised manner, to perform domain translation in opposite directions. Our method is not only better at capturing the shared information between two domains but is more generic and can be applied to a broader range of problems. The proposed framework performs well even in challenging cross-modal translations, such as video-driven speech reconstruction, for which other systems struggle to maintain correspondence.