Semi-Supervised Learning with Generative Adversarial Networks

by   Augustus Odena, et al.

We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N classes. At training time, D is made to predict which of N+1 classes the input belongs to, where an extra class is added to correspond to the outputs of G. We show that this method can be used to create a more data-efficient classifier and that it allows for generating higher quality samples than a regular GAN.


Multi-class Generative Adversarial Nets for Semi-supervised Image Classification

From generating never-before-seen images to domain adaptation, applicati...

An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks

We propose a method for semi-supervised training of structured-output ne...

Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks

We introduce a simple semi-supervised learning approach for images based...

O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks

In this paper, we propose Orthogonal Generative Adversarial Networks (O-...

DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks

We propose an action recognition framework using Gen- erative Adversaria...

Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network

Semantic segmentation has been a long standing challenging task in compu...

Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

In this paper we present a method for learning a discriminative classifi...

Please sign up or login with your details

Forgot password? Click here to reset