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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Disentangled representations have been commonly adopted to Age-invariant FaceRecognition (AiFR) tasks. However, these methods have reached some limitationswith (1) the requirement of large-scale face recognition (FR) training datawith age labels, which is limited in practice; (2) heavy deep networkarchitectures for high performance; and (3) their evaluations are usually takenplace on age-related face databases while neglecting the standard large-scaleFR databases to guarantee robustness. This work presents a novel LightweightAttentive Angular Distillation (LIAAD) approach to Large-scale Lightweight AiFRthat overcomes these limitations. Given two high-performance heavy networks asteachers with different specialized knowledge, LIAAD introduces a learningparadigm to efficiently distill the age-invariant attentive and angularknowledge from those teachers to a lightweight student network making it morepowerful with higher FR accuracy and robust against age factor. Consequently,LIAAD approach is able to take the advantages of both FR datasets with andwithout age labels to train an AiFR model. Far apart from prior distillationmethods mainly focusing on accuracy and compression ratios in closed-setproblems, our LIAAD aims to solve the open-set problem, i.e. large-scale facerecognition. Evaluations on LFW, IJB-B and IJB-C Janus, AgeDB andMegaFace-FGNet with one million distractors have demonstrated the efficiency ofthe proposed approach on light-weight structure. This work also presents a newlongitudinal face aging (LogiFace) database \footnote{This database will bemade available} for further studies in age-related facial problems in future.

LIAAD: Lightweight Attentive Angular Distillation for Large-scale Age-Invariant Face Recognition