MetaGAN: An Adversarial Approach To Few-Shot Learning

Authors:
Ruixiang ZHANG MILA
Tong Che MILA
Zoubin Ghahramani Uber and University of Cambridge
Yoshua Bengio U. Montreal
Yangqiu Song Hong Kong University of Science and Technology

Introduction:

In this paper, the authors propose a conceptually simple and general framework called MetaGAN for few-shot learning problems.

Abstract:

In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems. Most state-of-the-art few-shot classification models can be integrated with MetaGAN in a principled and straightforward way. By introducing an adversarial generator conditioned on tasks, we augment vanilla few-shot classification models with the ability to discriminate between real and fake data. We argue that this GAN-based approach can help few-shot classifiers to learn sharper decision boundary, which could generalize better. We show that with our MetaGAN framework, we can extend supervised few-shot learning models to naturally cope with unsupervised data. Different from previous work in semi-supervised few-shot learning, our algorithms can deal with semi-supervision at both sample-level and task-level. We give theoretical justifications of the strength of MetaGAN, and validate the effectiveness of MetaGAN on challenging few-shot image classification benchmarks.

You may want to know: