期刊论文

Cao Yuan

英文

Neurocomputing

0925-2312

2021

434

261-267

10.1016/j.neucom.2020.12.091

CRediT authorship contribution statement Xiangrui Xu: Methodology, Software, Validation, Formal analysis, Writing - original draft, Writing - review & editing. Yaqin Li: Investigation, Data curation, Visualization, Supervision, acquisition. Cao Yuan: Conceptualization, Resources, Project administration.

本校为第一机构

This paper explores conditional image generation with a One-Vs-All classifier based on the Generative Adversarial Networks (GANs). Instead of the real/fake discriminator used in vanilla GANs, we propose to extend the discriminator to a One-Vs-All classifier (GAN-OVA) that can distinguish each input data to its category label. Specifically, we feed certain additional information as conditions to the generator and take the discriminator as a One-Vs-All classifier to identify each conditional category. Our model can be applied to different diverge...