A Survey on Open-Set Image Recognition

TL;DR

This survey reviews recent developments in open-set image recognition, highlighting new methods, their performance on various datasets, and discussing future challenges in the field.

Contribution

It provides a comprehensive taxonomy and performance comparison of recent deep learning-based OSR methods, along with analysis and future research directions.

Findings

Recent OSR methods show improved accuracy on benchmark datasets

Deep neural networks are the predominant approach in OSR

Open issues include dataset diversity and real-world applicability

Abstract

Open-set image recognition (OSR) aims to both classify known-class samples and identify unknown-class samples in the testing set, which supports robust classifiers in many realistic applications, such as autonomous driving, medical diagnosis, security monitoring, etc. In recent years, open-set recognition methods have achieved more and more attention, since it is usually difficult to obtain holistic information about the open world for model training. In this paper, we aim to summarize the up-to-date development of recent OSR methods, considering their rapid development in recent two or three years. Specifically, we firstly introduce a new taxonomy, under which we comprehensively review the existing DNN-based OSR methods. Then, we compare the performances of some typical and state-of-the-art OSR methods on both coarse-grained datasets and fine-grained datasets under both standard-dataset setting and cross-dataset setting, and further give the analysis of the comparison. Finally, we discuss some open issues and possible future directions in this community.