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

Since the advent of generative adversarial networks (GANs), various lossfunctions have been developed and combined to constitute the overall trainingobjective function, in order to improve model performance or for specificlearning tasks. For instance, in image enhancement or restoration, there areoften several criteria to consider such as signal-noise ratio, smoothness,structures and details. However, when the optimization goal has more than oneadversarial loss, balancing multiple losses in the overall function becomes achallenging, critical and time-consuming problem. In this paper, we propose totackle the problem by means of efficient multi-objective optimization. Theproposed HypervolGAN adopts an adapted version of hypervolume maximizationmethod to effectively define the multi-objective training function for GAN. Wetested our proposed method on solving single image super-resolution problem.Experiments show that the proposed HypervolGAN is efficient in savingcomputational time and efforts for fine-tuning weights of various losses, andcan generate enhanced samples that have better quality than results given bybaseline GANs. The work explores the integration of adversarial learning andoptimization techniques, which can benefit not only image processing but also awide range of applications.

HypervolGAN: An efficient approach for GAN with multi-objective training function