DiscoGAN

A DiscoGAN is a generative adversarial network that generates images of products in domain B given an image in domain A. Illustrated in the following diagram is an architectural diagram of a DisoGAN network:

Figure 4.1: Architectural diagram of a DiscoGAN

The images generated in domain B resemble the images in domain A in both style and pattern. This relation can be learned without explicitly pairing images from the two domains during training. This is quite a powerful capability, given that the pairing of items is a time-consuming task. On a high level, it tries to learn two generator functions in the form of neural networks G_AB and G_BA so that an image x_A, when fed through the generator G_AB, produces an image x_AB, that looks realistic in domain B. Also, when this image x_AB is fed through the other generator network G_BA, it should produce an image x_ABA which should...