Lifelong Twin Generative Adversarial Networks

TL;DR

This paper introduces Lifelong Twin GANs, a novel continual learning generative model with a dual-generator architecture and a new training method that enables learning multiple tasks without forgetting.

Contribution

It proposes a new lifelong learning approach called Lifelong Adversarial Knowledge Distillation (LAKD) for twin GANs, facilitating continual learning across multiple datasets.

Findings

Effective knowledge transfer between generators.

Successful learning of multiple tasks without catastrophic forgetting.

Improved generative performance over existing lifelong GANs.

Abstract

In this paper, we propose a new continuously learning generative model, called the Lifelong Twin Generative Adversarial Networks (LT-GANs). LT-GANs learns a sequence of tasks from several databases and its architecture consists of three components: two identical generators, namely the Teacher and Assistant, and one Discriminator. In order to allow for the LT-GANs to learn new concepts without forgetting, we introduce a new lifelong training approach, namely Lifelong Adversarial Knowledge Distillation (LAKD), which encourages the Teacher and Assistant to alternately teach each other, while learning a new database. This training approach favours transferring knowledge from a more knowledgeable player to another player which knows less information about a previously given task.