OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations

TL;DR

OCGAN introduces a novel approach for one-class novelty detection by constraining latent space representations with adversarial training and gradient-based sampling, achieving state-of-the-art results.

Contribution

The paper proposes a new model that explicitly constrains the latent space for in-class examples using adversarial training and a gradient-based sampling technique.

Findings

Achieves state-of-the-art results on four datasets.

Effective in distinguishing in-class from out-of-class examples.

Uses a novel gradient-based sampling method for training.

Abstract

We present a novel model called OCGAN for the classical problem of one-class novelty detection, where, given a set of examples from a particular class, the goal is to determine if a query example is from the same class. Our solution is based on learning latent representations of in-class examples using a denoising auto-encoder network. The key contribution of our work is our proposal to explicitly constrain the latent space to exclusively represent the given class. In order to accomplish this goal, firstly, we force the latent space to have bounded support by introducing a tanh activation in the encoder's output layer. Secondly, using a discriminator in the latent space that is trained adversarially, we ensure that encoded representations of in-class examples resemble uniform random samples drawn from the same bounded space. Thirdly, using a second adversarial discriminator in the input space, we ensure all randomly drawn latent samples generate examples that look real. Finally, we introduce a gradient-descent based sampling technique that explores points in the latent space that generate potential out-of-class examples, which are fed back to the network to further train it to generate in-class examples from those points. The effectiveness of the proposed method is measured across four publicly available datasets using two one-class novelty detection protocols where we achieve state-of-the-art results.