Generative adversarial networks with adaptive learning strategy for noise-to-image synthesis

Yan GAN, Tao XIANG*, Hangcheng LIU, Mao YE, Mingliang ZHOU

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

2 Citations (Scopus)


Generative adversarial networks (GANs) directly learn from an unknown real distribution through adversarial training. However, training the generator only by the feedback of the discriminator cannot make GANs learn adaptively from the unknown complex real distribution, and for this reason the quality of generated images is unsatisfactory sometimes. To address this problem, we propose a framework for training GANs with an adaptive learning strategy from simpleness to complexity. First, we employ a pre-trained encoder and a generator to construct a simple task that looks like a real image. Second, an adaptive learning strategy is designed based on the mathematical expectation of the discriminating results of the real image and the simple task. The designed adaptive learning strategy is well compatible with various GANs architectures. Experimental results demonstrate the proposed method can improve the performance of existing GANs.

Original languageEnglish
Pages (from-to)6197-6206
Number of pages10
JournalNeural Computing and Applications
Issue number8
Early online date17 Nov 2022
Publication statusPublished - Mar 2023
Externally publishedYes

Bibliographical note

This work was supported by the National Key R&D Program of China under Grant 2022YFB3103500, the National Natural Science Foundation of China under Grants U20A20176, 62072062, 62106026 and 62176027, the Natural Science Foundation of Chongqing under Grants cstc2021jcyj-msxmX0273 and cstc2022ycjh-bgzxm0031, the Sichuan Science and Technology Program under Grant 2021YFQ0056, the China Postdoctoral Science Foundation under Grant 2020M683243, the Natural Science Foundation of Shandong Province under Grant ZR2019LZH016 and the Intelligent Terminal Key Laboratory of SiChuan Province under Grant SCITLAB-1016.


  • AutoEncoder
  • GANs
  • Learning strategy
  • Prior knowledge


Dive into the research topics of 'Generative adversarial networks with adaptive learning strategy for noise-to-image synthesis'. Together they form a unique fingerprint.

Cite this