A Survey on Open Set Recognition
It provides a comprehensive overview for researchers interested in OSR, but it is incremental as it summarizes existing works without introducing new methods.
This paper surveys Open Set Recognition (OSR), which addresses the problem of handling unknown instances not seen during training, and concludes that OSR can effectively manage such real-world scenarios where training data cannot cover all possible classes.
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.