GAN Memory with No Forgetting

by   Yulai Cong, et al.

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.



page 8

page 9

page 10

page 11

page 12

page 14

page 23

page 24


On catastrophic forgetting and mode collapse in Generative Adversarial Networks

Generative Adversarial Networks (GAN) are one of the most prominent tool...

Lifelong GAN: Continual Learning for Conditional Image Generation

Lifelong learning is challenging for deep neural networks due to their s...

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

Previous works on sequential learning address the problem of forgetting ...

Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation

Humans accumulate knowledge in a lifelong fashion. Modern deep neural ne...

Hypothesis-driven Stream Learning with Augmented Memory

Stream learning refers to the ability to acquire and transfer knowledge ...

Incremental Knowledge Based Question Answering

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

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.