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

Metric-based few-shot fine-grained image classification (FSFGIC) aims tolearn a transferable feature embedding network by estimating the similaritiesbetween query images and support classes from very few examples. In this work,we propose, for the first time, to introduce the non-linear data projectionconcept into the design of FSFGIC architecture in order to address the limitedsample problem in few-shot learning and at the same time to increase thediscriminability of the model for fine-grained image classification.Specifically, we first design a feature re-abstraction embedding network thathas the ability to not only obtain the required semantic features for effectivemetric learning but also re-enhance such features with finer details from inputimages. Then the descriptors of the query images and the support classes areprojected into different non-linear spaces in our proposed similarity metriclearning network to learn discriminative projection factors. This design caneffectively operate in the challenging and restricted condition of a FSFGICtask for making the distance between the samples within the same class smallerand the distance between samples from different classes larger and for reducingthe coupling relationship between samples from different categories.Furthermore, a novel similarity measure based on the proposed non-linear dataproject is presented for evaluating the relationships of feature informationbetween a query image and a support set. It is worth to note that our proposedarchitecture can be easily embedded into any episodic training mechanisms forend-to-end training from scratch. Extensive experiments on FSFGIC tasksdemonstrate the superiority of the proposed methods over the state-of-the-artbenchmarks.

NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification