English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Adversarial data augmentation has shown promise for training robust deepneural networks against unforeseen data shifts or corruptions. However, it isdifficult to define heuristics to generate effective fictitious targetdistributions containing "hard" adversarial perturbations that are largelydifferent from the source distribution. In this paper, we propose a novel andeffective regularization term for adversarial data augmentation. Wetheoretically derive it from the information bottleneck principle, whichresults in a maximum-entropy formulation. Intuitively, this regularization termencourages perturbing the underlying source distribution to enlarge predictiveuncertainty of the current model, so that the generated "hard" adversarialperturbations can improve the model robustness during training. Experimentalresults on three standard benchmarks demonstrate that our method consistentlyoutperforms the existing state of the art by a statistically significantmargin.

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness