Learning Unsupervised Cross-domain Image-to-Image Translation Using a Shared Discriminator
This work provides an incremental improvement for researchers working on unsupervised image-to-image translation, specifically in settings where source and target domains share similar semantics.
This paper addresses unsupervised cross-domain image-to-image translation, a task of transforming images from a source to a target domain without paired examples. The authors propose a method using a single shared discriminator between two GANs, achieving results comparable to attention-based methods without using attention mechanisms.
Unsupervised image-to-image translation is used to transform images from a source domain to generate images in a target domain without using source-target image pairs. Promising results have been obtained for this problem in an adversarial setting using two independent GANs and attention mechanisms. We propose a new method that uses a single shared discriminator between the two GANs, which improves the overall efficacy. We assess the qualitative and quantitative results on image transfiguration, a cross-domain translation task, in a setting where the target domain shares similar semantics to the source domain. Our results indicate that even without adding attention mechanisms, our method performs at par with attention-based methods and generates images of comparable quality.