A label-based adversarial robustness distillation method, ABSLD, re-temperates teacher soft labels per class to shrink the student's class-wise robust error gap and improves worst-class robustness and normalized standard deviation on CIFAR-10, CIFAR-100, and Tiny-ImageNet.
In: NeurIPS 2020 Workshop on Pre-registration in Machine Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Class-wise Fair Adversarial Training via Anti-Bias Soft Label Distillation
A label-based adversarial robustness distillation method, ABSLD, re-temperates teacher soft labels per class to shrink the student's class-wise robust error gap and improves worst-class robustness and normalized standard deviation on CIFAR-10, CIFAR-100, and Tiny-ImageNet.