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

Despite achieving state-of-the-art performance, deep learning methodsgenerally require a large amount of labeled data during training and may sufferfrom overfitting when the sample size is small. To ensure good generalizabilityof deep networks under small sample sizes, learning discriminative features iscrucial. To this end, several loss functions have been proposed to encouragelarge intra-class compactness and inter-class separability. In this paper, wepropose to enhance the discriminative power of features from a new perspectiveby introducing a novel neural network termed Relation-and-Margin learningNetwork (ReMarNet). Our method assembles two networks of different backbones soas to learn the features that can perform excellently in both of theaforementioned two classification mechanisms. Specifically, a relation networkis used to learn the features that can support classification based on thesimilarity between a sample and a class prototype; at the meantime, a fullyconnected network with the cross entropy loss is used for classification viathe decision boundary. Experiments on four image datasets demonstrate that ourapproach is effective in learning discriminative features from a small set oflabeled samples and achieves competitive performance against state-of-the-artmethods. Codes are available at https://github.com/liyunyu08/ReMarNet.

ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification