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

Discriminative features are critical for machine learning applications. Mostexisting deep learning approaches, however, rely on convolutional neuralnetworks (CNNs) for learning features, whose discriminant power is notexplicitly enforced. In this paper, we propose a novel approach to train deepCNNs by imposing the intra-class compactness and the inter-class separability,so as to enhance the learned features' discriminant power. To this end, weintroduce anchors, which are predefined vectors regarded as the centers foreach class and fixed during training. Discriminative features are obtained byconstraining the deep CNNs to map training samples to the corresponding anchorsas close as possible. We propose two principles to select the anchors, andmeasure the proximity of two points using the Euclidean and cosine distancemetric functions, which results in two novel loss functions. These lossfunctions require no sample pairs or triplets and can be efficiently optimizedby batch stochastic gradient descent. We test the proposed method on threebenchmark image classification datasets and demonstrate its promising results.

Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks