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

Lack of generalization to unseen domains/attacks is the Achilles heel of mostface presentation attack detection (FacePAD) algorithms. Existing attempts toenhance the generalizability of FacePAD solutions assume that data frommultiple source domains are available with a single entity to enablecentralized training. In practice, data from different source domains may becollected by diverse entities, who are often unable to share their data due tolegal and privacy constraints. While collaborative learning paradigms such asfederated learning (FL) can overcome this problem, standard FL methods areill-suited for domain generalization because they struggle to surmount the twinchallenges of handling non-iid client data distributions during training andgeneralizing to unseen domains during inference. In this work, a novelframework called Federated Split learning with Intermediate representationSampling (FedSIS) is introduced for privacy-preserving domain generalization.In FedSIS, a hybrid Vision Transformer (ViT) architecture is learned using acombination of FL and split learning to achieve robustness against statisticalheterogeneity in the client data distributions without any sharing of raw data(thereby preserving privacy). To further improve generalization to unseendomains, a novel feature augmentation strategy called intermediaterepresentation sampling is employed, and discriminative information fromintermediate blocks of a ViT is distilled using a shared adapter network. TheFedSIS approach has been evaluated on two well-known benchmarks forcross-domain FacePAD to demonstrate that it is possible to achievestate-of-the-art generalization performance without data sharing. Code:https://github.com/Naiftt/FedSIS

FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detection