A Survey on Open Set Recognition
arXiv:2109.00893 · doi:10.1109/AIKE52691.2021.00013
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.
arXiv comment17 pages, 6 figures
References in corpus (17)
- SSD: Single Shot MultiBox Detector
- Prototypical Networks for Few-shot Learning
- Towards Open World Recognition
- Deep Anomaly Detection with Outlier Exposure
- Deep Anomaly Detection Using Geometric Transformations
- Detecting Adversarial Samples from Artifacts
- On the (Statistical) Detection of Adversarial Examples
- The Extreme Value Machine
- Domain Adaptation for Visual Applications: A Comprehensive Survey
- Reducing Network Agnostophobia
- Unseen Class Discovery in Open-world Classification
- Lasso type classifiers with a reject option
- Deep CNN-based Multi-task Learning for Open-Set Recognition
- Open Vocabulary Learning on Source Code with a Graph-Structured Cache
- Online Open World Recognition
- Extreme Value Theory for Open Set Classification -- GPD and GEV Classifiers
- Known-class Aware Self-ensemble for Open Set Domain Adaptation