@InProceedings{ChenshenWu2018,
author="Chenshen Wu
and Luis Herranz
and Xialei Liu
and Joost Van de Weijer
and Bogdan Raducanu",
title="Memory Replay GANs: Learning to Generate New Categories without Forgetting",
booktitle="32nd Annual Conference on Neural Information Processing Systems",
year="2018",
pages="5966--5976",
abstract="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 (ie 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.",
optnote="LAMP; 600.106; 600.109; 602.200; 600.120",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3249), last updated on Tue, 08 Feb 2022 12:10:09 +0100",
file=":http://refbase.cvc.uab.es/files/WHL2018.pdf:PDF"
}