# Deep One-Class Classification Using Intra-Class Splitting

## TL;DR

This paper presents a novel deep learning approach for one-class classification that leverages intra-class splitting to improve decision boundaries, outperforming several baselines and matching state-of-the-art results.

## Contribution

It introduces a generic intra-class splitting method enabling deep neural networks to perform end-to-end one-class classification effectively.

## Key findings

- Outperforms seven baseline methods
- Achieves comparable or better results than state-of-the-art
- Effective on multiple image datasets

## Abstract

This paper introduces a generic method which enables to use conventional deep neural networks as end-to-end one-class classifiers. The method is based on splitting given data from one class into two subsets. In one-class classification, only samples of one normal class are available for training. During inference, a closed and tight decision boundary around the training samples is sought which conventional binary or multi-class neural networks are not able to provide. By splitting data into typical and atypical normal subsets, the proposed method can use a binary loss and defines an auxiliary subnetwork for distance constraints in the latent space. Various experiments on three well-known image datasets showed the effectiveness of the proposed method which outperformed seven baselines and had a better or comparable performance to the state-of-the-art.