Deep compact polyhedral conic classifier for open and closed set recognition
Pattern Recognition, vol.119, 2021 (SCI-Expanded, Scopus)
- Publication Type: Article / Article
- Volume: 119
- Publication Date: 2021
- Doi Number: 10.1016/j.patcog.2021.108080
- Journal Name: Pattern Recognition
- Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Applied Science & Technology Source, BIOSIS, Computer & Applied Sciences, INSPEC, MLA - Modern Language Association Database, zbMATH
- Keywords: Polyhedral conic classifier, Deep learning, Open set recognition, Image classification, Anomaly detection
- Eskisehir Osmangazi University Affiliated: Yes
Abstract
© 2021 Elsevier LtdIn this paper, we propose a new deep neural network classifier that simultaneously maximizes the inter-class separation and minimizes the intra-class variation by using the polyhedral conic classification function. The proposed method has one loss term that allows the margin maximization to maximize the inter-class separation and another loss term that controls the compactness of the class acceptance regions. Our proposed method has a nice geometric interpretation using polyhedral conic function geometry. We tested the proposed method on various visual classification problems including closed/open set recognition and anomaly detection. The experimental results show that the proposed method typically outperforms other state-of-the-art methods, and becomes a better choice compared to other tested methods especially for open set recognition type problems. The source code of the proposed method is available at https://github.com/bdrhn9/dc-epcc.