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

Generative Adversarial Networks (GANs) have shown promise in augmentingdatasets and boosting convolutional neural networks' (CNN) performance on imageclassification tasks. But they introduce more hyperparameters to tune as wellas the need for additional time and computational power to train supplementaryto the CNN. In this work, we examine the potential for Auxiliary-ClassifierGANs (AC-GANs) as a 'one-stop-shop' architecture for image classification,particularly in low data regimes. Additionally, we explore modifications to thetypical AC-GAN framework, changing the generator's latent space sampling schemeand employing a Wasserstein loss with gradient penalty to stabilize thesimultaneous training of image synthesis and classification. Throughexperiments on images of varying resolutions and complexity, we demonstratethat AC-GANs show promise in image classification, achieving competitiveperformance with standard CNNs. These methods can be employed as an'all-in-one' framework with particular utility in the absence of large amountsof training data.

Investigating the Potential of Auxiliary-Classifier GANs for Image Classification in Low Data Regimes