Skip to yearly menu bar Skip to main content


Memory Replay GANs: Learning to Generate New Categories without Forgetting

Chenshen Wu · Luis Herranz · Xialei Liu · yaxing wang · Joost van de Weijer · Bogdan Raducanu

Room 210 #30

Keywords: [ Computer Vision ] [ Adversarial Networks ]


Previous works on sequential learning address the problem of forgetting in discriminative models. 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. forgetting). Addressing this problem, we propose Memory Replay GANs (MeRGANs), a conditional GAN framework that integrates a memory replay generator. We study two methods to prevent forgetting by leveraging these replays, namely joint training with replay and replay alignment. Qualitative and quantitative experimental results in MNIST, SVHN and LSUN datasets show that our memory replay approach can generate competitive images while significantly mitigating the forgetting of previous categories.

Live content is unavailable. Log in and register to view live content