Reason and Discovery: A New Paradigm for Open Set Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-07 · 47 (7) · 5586-5599
DOI: 10.1109/tpami.2025.3552760 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-07. Verfasst von Yimin Fu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University, Cultivation Foundation for Excellent Doctoral Dissertation of the School of Automation of Northwestern Polytechnical University.
Abstract (Originalsprache)
Open set recognition (OSR) effectively enhances the reliability of pattern recognition systems by accurately identifying samples of unknown classes. However, the decision-making process in most existing OSR methods adheres to an ill-considered pipeline, where classification probabilities are inferred directly from overall feature representations, neglecting the reasoning about inherent relations. Besides, the handling of identified unknown samples is typically restricted to the assignment of a generic "unknown" class label but fails to explore underlying category information. To tackle the above challenges, we propose a new paradigm for OSR, entitled Reason and Discovery (RAD), which comprises two main modules: the Reason Module and the Discovery Module. Specifically, in the Reason Module, the distinction between known and unknown is performed from the perspective of reasoning the matching relations between topological information and appearance characteristics of discriminative regions. Then, the mixture and recombination of relation representations across classes are employed to provide diverse estimations of unknown distribution, thereby recalibrating OSR decision boundaries. Moreover, in the Discovery Module, the identified unknown samples are semantically grouped through a biased deep clustering process for discovering novel category information. Experimental results on various datasets indicate that the proposed method can achieve outstanding OSR performance and good novel category discovery efficacy.
Förderung
- National Natural Science Foundation of China
- Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University
- Cultivation Foundation for Excellent Doctoral Dissertation of the School of Automation of Northwestern Polytechnical University
Zitieren
APA
Fu, Y., Liu, Z., & Lyu, J. (2025). Reason and Discovery: A New Paradigm for Open Set Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(7), 5586-5599. https://doi.org/10.1109/tpami.2025.3552760
Vancouver
Fu Y, Liu Z, Lyu J. Reason and Discovery: A New Paradigm for Open Set Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(7):5586-5599. doi:10.1109/tpami.2025.3552760
BibTeX
@article{Fu2025,
author = {Fu, Yimin and Liu, Zhunga and Lyu, Jialin},
title = {Reason and Discovery: A New Paradigm for Open Set Recognition},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {7},
pages = {5586--5599},
doi = {10.1109/tpami.2025.3552760}
}
EUVIMED