Novelty Detection with GAN

TL;DR

This paper introduces a GAN-based approach for simultaneous classification and novelty detection, demonstrating improved performance over traditional methods by training a discriminator with a mixture generator.

Contribution

It presents a novel GAN framework that effectively detects novel inputs while classifying known categories, utilizing a mixture generator trained with Feature Matching loss.

Findings

Outperforms conventional novelty detection methods

Uses a multi-class discriminator with a mixture generator

Demonstrates effectiveness of GANs for novelty detection

Abstract

The ability of a classifier to recognize unknown inputs is important for many classification-based systems. We discuss the problem of simultaneous classification and novelty detection, i.e. determining whether an input is from the known set of classes and from which specific class, or from an unknown domain and does not belong to any of the known classes. We propose a method based on the Generative Adversarial Networks (GAN) framework. We show that a multi-class discriminator trained with a generator that generates samples from a mixture of nominal and novel data distributions is the optimal novelty detector. We approximate that generator with a mixture generator trained with the Feature Matching loss and empirically show that the proposed method outperforms conventional methods for novelty detection. Our findings demonstrate a simple, yet powerful new application of the GAN framework for the task of novelty detection.