상세 보기
Construction of Error Correcting Output Codes for Robust Deep Neural Networks Based on Label Grouping Scheme
- Youn, Hwiyoung;
- Kwon, Soonhee;
- Lee, Hyunhee;
- Kim, Jiho;
- Hong, Songnam;
- ... Shin, Dong-Joon
Citations
SCOPUS
1초록
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.
키워드
Adversarial robustness; Classification; Error-correcting output codes; Label grouping; Linear discriminant analysis; Codes (symbols); Discriminant analysis; Errors; Network coding; Adversarial robustness; Binary classifiers; Code construction; Code frameworks; Error-correcting output codes; Label grouping; Linear discriminant analyze; Multi-class classifier; Network-based; Simple++; Deep neural networks
- 제목
- Construction of Error Correcting Output Codes for Robust Deep Neural Networks Based on Label Grouping Scheme
- 저자
- Youn, Hwiyoung; Kwon, Soonhee; Lee, Hyunhee; Kim, Jiho; Hong, Songnam; Shin, Dong-Joon
- 발행일
- 2022-01
- 유형
- Conference Paper
- 저널명
- Proceedings of 2021 7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021
- 페이지
- 51 ~ 55