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

Model robustness is vital for the reliable deployment of machine learningmodels in real-world applications. Recent studies have shown that dataaugmentation can result in model over-relying on features in the low-frequencydomain, sacrificing performance against low-frequency corruptions, highlightinga connection between frequency and robustness. Here, we take one step furtherto more directly study the frequency bias of a model through the lens of itsJacobians and its implication to model robustness. To achieve this, we proposeJacobian frequency regularization for models' Jacobians to have a larger ratioof low-frequency components. Through experiments on four image datasets, weshow that biasing classifiers towards low (high)-frequency components can bringperformance gain against high (low)-frequency corruption and adversarialperturbation, albeit with a tradeoff in performance for low (high)-frequencycorruption. Our approach elucidates a more direct connection between thefrequency bias and robustness of deep learning models.

How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?