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

In this paper, we design and evaluate a convolutional autoencoder thatperturbs an input face image to impart privacy to a subject. Specifically, theproposed autoencoder transforms an input face image such that the transformedimage can be successfully used for face recognition but not for genderclassification. In order to train this autoencoder, we propose a novel trainingscheme, referred to as semi-adversarial training in this work. The training isfacilitated by attaching a semi-adversarial module consisting of a pseudogender classifier and a pseudo face matcher to the autoencoder. The objectivefunction utilized for training this network has three terms: one to ensure thatthe perturbed image is a realistic face image; another to ensure that thegender attributes of the face are confounded; and a third to ensure thatbiometric recognition performance due to the perturbed image is not impacted.Extensive experiments confirm the efficacy of the proposed architecture inextending gender privacy to face images.

Semi-Adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images