Construction of Error Correcting Output Codes for Robust Deep Neural Networks Based on Label Grouping Scheme

Citations

SCOPUS

1

초록

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 robustnessClassificationError-correcting output codesLabel groupingLinear discriminant analysisCodes (symbols)Discriminant analysisErrorsNetwork codingAdversarial robustnessBinary classifiersCode constructionCode frameworksError-correcting output codesLabel groupingLinear discriminant analyzeMulti-class classifierNetwork-basedSimple++Deep neural networks
제목
Construction of Error Correcting Output Codes for Robust Deep Neural Networks Based on Label Grouping Scheme
저자
Youn, HwiyoungKwon, SoonheeLee, HyunheeKim, JihoHong, SongnamShin, Dong-Joon
DOI
10.1109/IC-NIDC54101.2021.9660486
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