Well File:

 Joost van de Weijer




Memory Replay GANs: Learning to Generate New Categories without Forgetting

Neural Information Processing Systems

In this paper we consider the case of generative models. In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion. We first show that sequential fine tuning renders the network unable to properly generate images from previous categories (i.e.