Understanding and combating robust overfitting via input loss landscape analysis and regularization
Authors:
- Lin LiLLLin Li
- Michael SpratlingMSMichael Spratling
Open Access
- 1 December 2022
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 136
Abstract
No abstract availableKeywords
All Related Versions
This publication has 4 references indexed in Scilit:
- A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologiesPattern Recognition, 2022
- Consistency Regularization for Adversarial RobustnessProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Deep learningNature, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015