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 the field of face recognition, it is always a hot research topic toimprove the loss solution to make the face features extracted by the networkhave greater discriminative power. Research works in recent years has improvedthe discriminative power of the face model by normalizing softmax to the cosinespace step by step and then adding a fixed penalty margin to reduce theintra-class distance to increase the inter-class distance. Although a greatdeal of previous work has been done to optimize the boundary penalty to improvethe discriminative power of the model, adding a fixed margin penalty to thedepth feature and the corresponding weight is not consistent with the patternof data in the real scenario. To address this issue, in this paper, we proposea novel loss function, InterFace, releasing the constraint of adding a marginpenalty only between the depth feature and the corresponding weight to push theseparability of classes by adding corresponding margin penalties between thedepth features and all weights. To illustrate the advantages of InterFace overa fixed penalty margin, we explained geometrically and comparisons on a set ofmainstream benchmarks. From a wider perspective, our InterFace has advanced thestate-of-the-art face recognition performance on five out of thirteenmainstream benchmarks. All training codes, pre-trained models, and traininglogs, are publicly released\footnote{$https://github.com/iamsangmeng/InterFace$}.

InterFace:Adjustable Angular Margin Inter-class Loss for Deep Face Recognition