# One-Class Convolutional Neural Network

## TL;DR

This paper introduces a novel CNN-based method for one class classification that uses Gaussian noise in the latent space as a pseudo-negative class, enabling effective learning of decision boundaries with any pre-trained CNN.

## Contribution

The paper proposes a flexible one class classification approach using pre-trained CNNs and Gaussian noise in latent space, showing significant improvements over existing methods.

## Key findings

- Achieves superior performance on multiple datasets.
- Compatible with any pre-trained CNN architecture.
- Outperforms recent state-of-the-art techniques.

## Abstract

We present a novel Convolutional Neural Network (CNN) based approach for one class classification. The idea is to use a zero centered Gaussian noise in the latent space as the pseudo-negative class and train the network using the cross-entropy loss to learn a good representation as well as the decision boundary for the given class. A key feature of the proposed approach is that any pre-trained CNN can be used as the base network for one class classification. The proposed One Class CNN (OC-CNN) is evaluated on the UMDAA-02 Face, Abnormality-1001, FounderType-200 datasets. These datasets are related to a variety of one class application problems such as user authentication, abnormality detection and novelty detection. Extensive experiments demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. The source code is available at : github.com/otkupjnoz/oc-cnn.