# Open-Set Recognition Using Intra-Class Splitting

## TL;DR

This paper introduces an open-set recognition method using intra-class splitting to distinguish known from unknown classes, improving classification accuracy and outperforming existing approaches.

## Contribution

It presents a novel intra-class splitting technique combined with regularization to enhance open-set recognition performance in deep neural networks.

## Key findings

- Outperformed baseline methods on five image datasets.
- Achieved significant improvements over state-of-the-art techniques.
- Effectively modeled unknown classes using atypical normal samples.

## Abstract

This paper proposes a method to use deep neural networks as end-to-end open-set classifiers. It is based on intra-class data splitting. In open-set recognition, only samples from a limited number of known classes are available for training. During inference, an open-set classifier must reject samples from unknown classes while correctly classifying samples from known classes. The proposed method splits given data into typical and atypical normal subsets by using a closed-set classifier. This enables to model the abnormal classes by atypical normal samples. Accordingly, the open-set recognition problem is reformulated into a traditional classification problem. In addition, a closed-set regularization is proposed to guarantee a high closed-set classification performance. Intensive experiments on five well-known image datasets showed the effectiveness of the proposed method which outperformed the baselines and achieved a distinct improvement over the state-of-the-art methods.