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

Face recognition has made extraordinary progress owing to the advancement ofdeep convolutional neural networks (CNNs). The central task of facerecognition, including face verification and identification, involves facefeature discrimination. However, the traditional softmax loss of deep CNNsusually lacks the power of discrimination. To address this problem, recentlyseveral loss functions such as center loss, large margin softmax loss, andangular softmax loss have been proposed. All these improved losses share thesame idea: maximizing inter-class variance and minimizing intra-class variance.In this paper, we propose a novel loss function, namely large margin cosineloss (LMCL), to realize this idea from a different perspective. Morespecifically, we reformulate the softmax loss as a cosine loss by $L_2$normalizing both features and weight vectors to remove radial variations, basedon which a cosine margin term is introduced to further maximize the decisionmargin in the angular space. As a result, minimum intra-class variance andmaximum inter-class variance are achieved by virtue of normalization and cosinedecision margin maximization. We refer to our model trained with LMCL asCosFace. Extensive experimental evaluations are conducted on the most popularpublic-domain face recognition datasets such as MegaFace Challenge, YoutubeFaces (YTF) and Labeled Face in the Wild (LFW). We achieve the state-of-the-artperformance on these benchmarks, which confirms the effectiveness of ourproposed approach.

CosFace: Large Margin Cosine Loss for Deep Face Recognition