SPGAN: Siamese projection Generative Adversarial Networks

Yan GAN, Tao XIANG*, Deqiang OUYANG, Mingliang ZHOU, Mao YE

*Corresponding author for this work

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

1 Citation (Scopus)


Noise-to-image synthesis continues to be challenging, despite the application of the advanced loss functions in Generative Adversarial Networks (GANs). The main issue lies in the fact that discriminators employ hard margin classification, which is susceptible to misclassification. Moreover, the features of real image distribution learned by the generator are limited during adversarial training, thus the generated images are visually inferior to the real images. To tackle these challenges, a GAN method based on Siamese projection network (abbreviated as SPGAN) is proposed to learn a similarity measurement of features for image synthesis. Then, the similarity measurement is incorporated into the loss functions of the generator and discriminator, forming a similar feature adversarial learning. Through similar feature adversarial learning, SPGAN encourages the discriminator to maximize the dissimilarity between the features of real and generated images during recognition process. Simultaneously, it encourages the generator to synthesize images that contain more features resembling those of real images. Furthermore, we extend the SPGAN method by rewriting five representative loss functions, showcasing its compatibility with different loss functions. Experimental results demonstrate that the performance of SPGAN outperforms the advanced loss functions.

Original languageEnglish
Article number111353
JournalKnowledge-Based Systems
Publication statusPublished - 15 Feb 2024
Externally publishedYes

Bibliographical note

Thank you to Mr. Tao Xiang, Mr. Deqiang Ouyang, Mr. Mingliang Zhou, and Mr. Mao Ye for their suggestions about method, writing, and revision. Our work was supported by the National Key R&D Program of China (2022YFB3103500), National Natural Science Foundation of China (U20A20176, 62072062 and 62106026), National Postdoctoral Researcher Funding Program (GZC20233323), Natural Science Foundation of Chongqing (cstc2021jcyj-msxmX0273, cstc2022ycjh-bgzxm0031 and CSTB2023NSCQ-MSX1020), and the Fundamental Research Funds for the Central Universities (2023CDJXY-039).


  • GANs
  • Image synthesis
  • Siamese projection network
  • Similar feature adversarial learning


Dive into the research topics of 'SPGAN: Siamese projection Generative Adversarial Networks'. Together they form a unique fingerprint.

Cite this