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

Convolutional Neural Networks (CNNs) have become the state-of-the-art methodto learn from image data. However, recent research shows that they may includea texture and colour bias in their representation, contrary to the intuitionthat they learn the shapes of the image content and to human biologicallearning. Thus, recent works have attempted to increase the shape bias in CNNsin order to train more robust and accurate networks on tasks. One such approachuses style-transfer in order to remove texture clues from the data. This workreproduces this methodology on four image classification datasets, as well asextends the method to use domain-adversarial training in order to furtherincrease the shape bias in the learned representation. The results show theproposed method increases the robustness and shape bias of the CNNs, while itdoes not provide a gain in accuracy.

Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods