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

preprint · arXiv (Cornell University) · 2023

Dynamically Masked Discriminator for Generative Adversarial Networks

Wentian Zhang, Haozhe Liu, Bing Li, Jinheng Xie, Yawen Huang, Yuexiang Li, Yefeng Zheng, Bernard Ghanem

Cited by 1Open access

Abstract

Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However, the distribution of generated data changes throughout the training process, which is difficult for the discriminator to learn. In this paper, we propose a novel method for GANs from the viewpoint of online continual learning. We observe that the discriminator model, trained on historically generated data, often slows down its adaptation to the changes in the new arrival generated data, which accordingly decreases the quality of generated results. By treating the generated data in training as a stream, we propose to detect whether the discriminator slows down the learning of new knowledge in generated data. Therefore, we can explicitly enforce the discriminator to learn new knowledge fast. Particularly, we propose a new discriminator, which automatically detects its retardation and then dynamically masks its features, such that the discriminator can adaptively learn the temporally-vary distribution of generated data. Experimental results show our method outperforms the state-of-the-art approaches.

Cite this paper

APA 7

Zhang, W., Liu, H., Li, B., Xie, J., Huang, Y., Li, Y., Zheng, Y., & Ghanem, B. (2023). Dynamically Masked Discriminator for Generative Adversarial Networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2306.07716

MLA 9

Zhang, Wentian, et al. “Dynamically Masked Discriminator for Generative Adversarial Networks.” arXiv (Cornell University), 2023, https://doi.org/10.48550/arxiv.2306.07716.

Chicago

Zhang, Wentian, Haozhe Liu, Bing Li, Jinheng Xie, Yawen Huang, Yuexiang Li, Yefeng Zheng, and Bernard Ghanem. 2023. “Dynamically Masked Discriminator for Generative Adversarial Networks.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2306.07716.

Harvard

Zhang, W. et al. (2023) ‘Dynamically Masked Discriminator for Generative Adversarial Networks’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.2306.07716.

BibTeX
@misc{zhang2023dynamically,
  title = {{Dynamically Masked Discriminator for Generative Adversarial Networks}},
  author = {Zhang, Wentian and Liu, Haozhe and Li, Bing and Xie, Jinheng and Huang, Yawen and Li, Yuexiang and Zheng, Yefeng and Ghanem, Bernard},
  journal = {arXiv (Cornell University)},
  year = {2023},
  doi = {10.48550/arxiv.2306.07716}
}

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