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

Learning discriminative deep feature embeddings by using million-scalein-the-wild datasets and margin-based softmax loss is the currentstate-of-the-art approach for face recognition. However, the memory andcomputing cost of the Fully Connected (FC) layer linearly scales up to thenumber of identities in the training set. Besides, the large-scale trainingdata inevitably suffers from inter-class conflict and long-tailed distribution.In this paper, we propose a sparsely updating variant of the FC layer, namedPartial FC (PFC). In each iteration, positive class centers and a random subsetof negative class centers are selected to compute the margin-based softmaxloss. All class centers are still maintained throughout the whole trainingprocess, but only a subset is selected and updated in each iteration.Therefore, the computing requirement, the probability of inter-class conflict,and the frequency of passive update on tail class centers, are dramaticallyreduced. Extensive experiments across different training data and backbones(e.g. CNN and ViT) confirm the effectiveness, robustness and efficiency of theproposed PFC. The source code is available at\https://github.com/deepinsight/insightface/tree/master/recognition.

Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC