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

The prototypical network (ProtoNet) is a few-shot learning framework thatperforms metric learning and classification using the distance to prototyperepresentations of each class. It has attracted a great deal of attentionrecently since it is simple to implement, highly extensible, and performs wellin experiments. However, it only takes into account the mean of the supportvectors as prototypes and thus it performs poorly when the support set has highvariance. In this paper, we propose to combine ProtoNet with local Fisherdiscriminant analysis to reduce the local within-class covariance and increasethe local between-class covariance of the support set. We show the usefulnessof the proposed method by theoretically providing an expected risk bound andempirically demonstrating its superior classification accuracy on miniImageNetand tieredImageNet.

LFD-ProtoNet: Prototypical Network Based on Local Fisher Discriminant Analysis for Few-shot Learning