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

by   Saman Motamed, et al.

From generating never-before-seen images to domain adaptation, applications of Generative Adversarial Networks (GANs) spread wide in the domain of vision and graphics problems. With the remarkable ability of GANs in learning the distribution and generating images of a particular class, they can be used for semi-supervised classification tasks. However, the problem is that if two classes of images share similar characteristics, the GAN might learn to generalize and hinder the classification of the two classes. In this paper, we use various images from MNIST and Fashion-MNIST datasets to illustrate how similar images cause the GAN to generalize, leading to the poor classification of images. We propose a modification to the traditional training of GANs that allows for improved multi-class classification in similar classes of images in a semi-supervised learning framework.


page 4

page 5


Semi-Supervised Learning with Generative Adversarial Networks

We extend Generative Adversarial Networks (GANs) to the semi-supervised ...

Generalizing semi-supervised generative adversarial networks to regression

In this work, we generalize semi-supervised generative adversarial netwo...

Teaching a GAN What Not to Learn

Generative adversarial networks (GANs) were originally envisioned as uns...

Improved Techniques for Training GANs

We present a variety of new architectural features and training procedur...

Semi-supervised GAN for Classification of Multispectral Imagery Acquired by UAVs

Unmanned aerial vehicles (UAV) are used in precision agriculture (PA) to...

Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect

Despite being impactful on a variety of problems and applications, the g...

Please sign up or login with your details

Forgot password? Click here to reset