Recent Advances in Open Set Recognition: A Survey

TLDR

Real‑world recognition tasks often lack exhaustive training samples, making open set recognition (OSR)—where classifiers must handle unseen classes at test time—a more realistic scenario. This survey reviews existing OSR techniques, including definitions, model representations, datasets, evaluation criteria, and algorithm comparisons. The authors analyze OSR’s connections to zero‑shot, few‑shot, reject‑option classification, and review open‑world recognition as a natural extension. The survey identifies limitations of current OSR methods and proposes promising future research directions.

Abstract

In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, evaluation criteria, and algorithm comparisons. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also review the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field.