GAN Memory with No Forgetting

06/13/2020
by   Yulai Cong, et al.
0

Seeking to address the fundamental issue of memory in lifelong learning, we propose a GAN memory that is capable of realistically remembering a stream of generative processes with no forgetting. Our GAN memory is based on recognizing that one can modulate the “style” of a GAN model to form perceptually-distant targeted generation. Accordingly, we propose to do sequential style modulations atop a well-behaved base GAN model, to form sequential targeted generative models, while simultaneously benefiting from the transferred base knowledge. Experiments demonstrate the superiority of our method over existing approaches and its effectiveness in alleviating catastrophic forgetting for lifelong classification problems.

READ FULL TEXT

Authors

page 8

page 9

page 10

page 11

page 12

page 14

page 23

page 24

07/11/2018

On catastrophic forgetting and mode collapse in Generative Adversarial Networks

Generative Adversarial Networks (GAN) are one of the most prominent tool...
07/23/2019

Lifelong GAN: Continual Learning for Conditional Image Generation

Lifelong learning is challenging for deep neural networks due to their s...
09/06/2018

Memory Replay GANs: learning to generate images from new categories without forgetting

Previous works on sequential learning address the problem of forgetting ...
04/24/2021

Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation

Humans accumulate knowledge in a lifelong fashion. Modern deep neural ne...
04/06/2021

Hypothesis-driven Stream Learning with Augmented Memory

Stream learning refers to the ability to acquire and transfer knowledge ...
01/18/2021

Incremental Knowledge Based Question Answering

In the past years, Knowledge-Based Question Answering (KBQA), which aims...
01/19/2019

Convolution Forgetting Curve Model for Repeated Learning

Most of mathematic forgetting curve models fit well with the forgetting ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.