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

This work addresses the problem of anonymizing the identity of faces in adataset of images, such that the privacy of those depicted is not violated,while at the same time the dataset is useful for downstream task such as fortraining machine learning models. To the best of our knowledge, we are thefirst to explicitly address this issue and deal with two major drawbacks of theexisting state-of-the-art approaches, namely that they (i) require the costlytraining of additional, purpose-trained neural networks, and/or (ii) fail toretain the facial attributes of the original images in the anonymizedcounterparts, the preservation of which is of paramount importance for theiruse in downstream tasks. We accordingly present a task-agnostic anonymizationprocedure that directly optimizes the images' latent representation in thelatent space of a pre-trained GAN. By optimizing the latent codes directly, weensure both that the identity is of a desired distance away from the original(with an identity obfuscation loss), whilst preserving the facial attributes(using a novel feature-matching loss in FaRL's deep feature space). Wedemonstrate through a series of both qualitative and quantitative experimentsthat our method is capable of anonymizing the identity of the images whilst --crucially -- better-preserving the facial attributes. We make the code and thepre-trained models publicly available at: https://github.com/chi0tzp/FALCO.

Attribute-preserving Face Dataset Anonymization via Latent Code Optimization