One-Class Convolutional Neural Network
This addresses one-class classification problems such as user authentication and abnormality detection, offering a novel method for a known bottleneck.
The paper tackles one-class classification by using a CNN with Gaussian noise as a pseudo-negative class and cross-entropy loss, achieving significant improvements over state-of-the-art methods on datasets like UMDAA-02 Face and Abnormality-1001.
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.