Construction of Error Correcting Output Codes for Robust Deep Neural Networks Based on Label Grouping Scheme
- Authors
- Youn, Hwiyoung; Kwon, Soonhee; Lee, Hyunhee; Kim, Jiho; Hong, Songnam; Shin, Dong-Joon
- Issue Date
- Jan-2022
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Adversarial robustness; Classification; Error-correcting output codes; Label grouping; Linear discriminant analysis
- Citation
- Proceedings of 2021 7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021, pp.51 - 55
- Indexed
- SCOPUS
- Journal Title
- Proceedings of 2021 7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021
- Start Page
- 51
- End Page
- 55
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/139799
- DOI
- 10.1109/IC-NIDC54101.2021.9660486
- ISSN
- 0000-0000
- Abstract
- Error-Correcting Output Codes (ECOCs) have been proposed to construct multi-class classifiers using simple binary classifiers. Recently, the principle of ECOCs has been employed for improving the robustness of deep classifiers. In this paper, a novel ECOC framework is developed by presenting a novel label grouping and code-construction method. The proposed label grouping is based on linear discriminant analysis (LDA) similarity. Via simulations, it is demonstrated that deep classifiers trained with the proposed ECOC yield better classification performance on pure data and better adversarial robustness than the state-of-the-art deep neural classifiers using ECOCs.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/139799)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.