Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

article · IEEE Transactions on Multimedia · 2022

Discriminator-Quality Evaluation GAN

Xuesong Wang, Ke Jin, Yi Kong, C. L. Philip Chen, Yuhu Cheng

Cited by 7Abstract and details only

Abstract

In existing generative adversarial networks (standard GAN and its variants), the discriminator is trained for recognizing the real data as positive while the generated data as negative. This kind of positive-negative classification criterion ignores the fact that the discriminator is a non-objective evaluator, which means that the image quality evaluated by the discriminator may fluctuate during the whole training progress. Considering this fact, we propose a novel GAN framework called Discriminator-Quality Evaluation GAN (DQE-GAN) by using the discriminator outputs to evaluate image quality. By dynamically classifying images into high discriminator-quality and low discriminator-quality samples, every adversarial iteration step can be more reasonable and objective. The convergence of DQE-GAN framework can be theoretically proved. Through extensive experiments, we demonstrate DQE-GANs’ ability of achieving better generated images faster and more stable.

Cite this paper

APA 7

Wang, X., Jin, K., Kong, Y., Chen, C. L. P., & Cheng, Y. (2022). Discriminator-Quality Evaluation GAN. IEEE Transactions on Multimedia, 25, 4081–4093. https://doi.org/10.1109/tmm.2022.3171084

MLA 9

Wang, Xuesong, et al. “Discriminator-Quality Evaluation GAN.” IEEE Transactions on Multimedia, vol. 25, 2022, pp. 4081–93, https://doi.org/10.1109/tmm.2022.3171084.

Chicago

Wang, Xuesong, Ke Jin, Yi Kong, C. L. Philip Chen, and Yuhu Cheng. 2022. “Discriminator-Quality Evaluation GAN.” IEEE Transactions on Multimedia 25: 4081–93. https://doi.org/10.1109/tmm.2022.3171084.

Harvard

Wang, X. et al. (2022) ‘Discriminator-Quality Evaluation GAN’, IEEE Transactions on Multimedia, 25, pp. 4081–4093. Available at: https://doi.org/10.1109/tmm.2022.3171084.

BibTeX
@article{wang2022discriminator,
  title = {{Discriminator-Quality Evaluation GAN}},
  author = {Wang, Xuesong and Jin, Ke and Kong, Yi and Chen, C. L. Philip and Cheng, Yuhu},
  journal = {IEEE Transactions on Multimedia},
  volume = {25},
  pages = {4081--4093},
  year = {2022},
  doi = {10.1109/tmm.2022.3171084}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers