Managing the unknown: a survey on Open Set Recognition and tangential areas
In real-world scenarios classification models are often required to perform robustly when predicting samples belonging to classes that have not appeared during its training stage. Open Set Recognition addresses this issue by devising models capable of detecting unknown classes from samples arriving during the testing phase, while maintaining a good level of performance in the classification of samples belonging to known classes. This review comprehensively overviews the recent literature related to Open Set Recognition, identifying common practices, limitations, and connections of this field with other machine learning research areas, such as continual learning, out-of-distribution detection, novelty detection, and uncertainty estimation. Our work also uncovers open problems and suggests several research directions that may motivate and articulate future efforts towards more safe Artificial Intelligence methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningNovelty DetectionOpen Set LearningOut-of-Distribution DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Deep Learning and Open Set Malware Classification: A Survey
As the Internet is growing rapidly these years, the variant of malicious software, which often referred to as malware, has become one of the major and serious threats to Internet users. The dramatic increase of malware h…
BIG-bench Machine LearningClassificationDeep LearningGeneral Classification+3A Survey on Open Set Recognition
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 adv…
Multi-class ClassificationNovelty DetectionOpen Set LearningSurveyModel Evaluation for Domain Identification of Unknown Classes in Open-World Recognition: A Proposal
Open-World Recognition (OWR) is an emerging field that makes a machine learning model competent in rejecting the unknowns, managing them, and incrementally adding novel samples to the base knowledge. However, this broad …
AutoMLTransfer LearningBalanced Truncation via Tangential Interpolation
This paper examines the construction of rth-order truncated balanced realizations via tangential interpolation at r specified interpolation points. It is demonstrated that when the truncated Hankel singular values are ne…
Recent Advances in Open Set Recognition: A Survey
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 …
General ClassificationOpen Set LearningSurvey