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

CNNs perform remarkably well when the training and test distributions arei.i.d, but unseen image corruptions can cause a surprisingly large drop inperformance. In various real scenarios, unexpected distortions, such as randomnoise, compression artefacts, or weather distortions are common phenomena.Improving performance on corrupted images must not result in degraded i.i.dperformance - a challenge faced by many state-of-the-art robust approaches.Image corruption types have different characteristics in the frequency spectrumand would benefit from a targeted type of data augmentation, which, however, isoften unknown during training. In this paper, we introduce a mixture of twoexpert models specializing in high and low-frequency robustness, respectively.Moreover, we propose a new regularization scheme that minimizes the totalvariation (TV) of convolution feature-maps to increase high-frequencyrobustness. The approach improves on corrupted images without degradingin-distribution performance. We demonstrate this on ImageNet-C and also forreal-world corruptions on an automotive dataset, both for object classificationand object detection.

Improving robustness against common corruptions with frequency biased models