Deep One-Class Classification Using Intra-Class Splitting
It addresses the problem of one-class classification for scenarios where only normal class data is available, offering a generic method that improves upon existing approaches.
The paper tackles one-class classification by enabling deep neural networks to function as end-to-end one-class classifiers through intra-class splitting, achieving performance that outperformed seven baselines and was comparable to state-of-the-art methods on three image datasets.
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.