A Survey on Open Set Recognition

TL;DR

This survey comprehensively reviews open set recognition, highlighting its importance in real-world scenarios where models encounter unknown classes, and discusses recent progress, challenges, and future directions.

Contribution

It categorizes existing OSR models, analyzes their advantages and disadvantages, and explores their relationships with related tasks like classification and novelty detection.

Findings

OSR effectively handles unknown instances in real-world applications.

Recent progress includes new models and techniques for improved recognition.

Future research directions involve better integration with related tasks and real-world deployment.

Abstract

Open Set Recognition (OSR) is about dealing with unknown situations that were not learned by the models during training. In this paper, we provide a survey of existing works about OSR and distinguish their respective advantages and disadvantages to help out new researchers interested in the subject. The categorization of OSR models is provided along with an extensive summary of recent progress. Additionally, the relationships between OSR and its related tasks including multi-class classification and novelty detection are analyzed. It is concluded that OSR can appropriately deal with unknown instances in the real-world where capturing all possible classes in the training data is not practical. Lastly, applications of OSR are highlighted and some new directions for future research topics are suggested.