Deep Fuzzy Tree for Large-Scale Hierarchical Visual Classification

Wang, Yu; Hu, Qinghua; Zhu, Pengfei; Li, Linhao; Lu, Bingxu; Garibaldi, Jonathan M.; Li, Xianling

Abstract

Deep learning models often use a flat softmax layer to classify samples after feature extraction in visual classification tasks. However, it is hard to make a single decision of finding the true label from massive classes. In this scenario, hierarchical classification is proved to be an effective solution and can be utilized to replace the softmax layer. A key issue of hierarchical classification is to construct a good label structure, which is very significant for classification performance. Several works have been proposed to address the issue, but they have some limits and are almost designed heuristically. In this paper, inspired by fuzzy rough set theory, we propose a deep fuzzy tree model which learns a better tree structure and classifiers for hierarchical classification with theory guarantee. Experimental results show the effectiveness and efficiency of the proposed model in various visual classification datasets.

Citation

Wang, Y., Hu, Q., Zhu, P., Li, L., Lu, B., Garibaldi, J. M., & Li, X. (2020). Deep Fuzzy Tree for Large-Scale Hierarchical Visual Classification. IEEE Transactions on Fuzzy Systems, 28(7), 1395-1406. https://doi.org/10.1109/tfuzz.2019.2936801

• Journal Article Type: Article
• Acceptance Date: Aug 15, 2019
• Online Publication Date: Aug 21, 2019
• Publication Date: 2020-07
• Deposit Date: Sep 24, 2019
• Publicly Available Date: Sep 24, 2019
• Journal: IEEE Transactions on Fuzzy Systems
• Print ISSN: 1063-6706
• Electronic ISSN: 1941-0034
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 28
• Issue: 7
• Pages: 1395-1406
• DOI: https://doi.org/10.1109/tfuzz.2019.2936801
• Keywords: Control and Systems Engineering; Computational Theory and Mathematics; Applied Mathematics; Artificial Intelligence
• Public URL: https://nottingham-repository.worktribe.com/output/2655524
• Publisher URL: https://ieeexplore.ieee.org/abstract/document/8809246
• Additional Information: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.