Towards Adversarially Robust Dataset Distillation by Curvature Regularization

arXiv:2403.10045v1 Announce Type: new
Abstract: Dataset distillation (DD) allows datasets to be distilled to fractions of their original size while preserving the rich distributional information so that models trained on the distilled datasets can achieve a comparable accuracy while saving significant computational loads. Recent research in this area has been focusing on improving the accuracy of models trained on distilled datasets. In this paper, we aim to explore a new perspective of DD. We study how to embed adversarial robustness …

abstract accuracy arxiv computational cs.cv cs.lg dataset datasets distillation fractions information regularization research robust saving type