University of Surrey

Test tubes in the lab Research in the ATI Dance Research

SP-GAN: Self-growing and Pruning Generative Adversarial Networks

Song, Xiaoning, Chen, Yao, Feng, Zhenhua, Hu, Guosheng, Yu, Dong-Jun and Wu, Xiao-Jun (2020) SP-GAN: Self-growing and Pruning Generative Adversarial Networks IEEE Transactions on Neural Networks and Learning Systems.

[img] Text
TNNLS2020.pdf - Accepted version Manuscript
Restricted to Repository staff only until 22 June 2022.

Download (1MB)


This paper presents a new Self-growing and Pruning Generative Adversarial Network (SP-GAN) for realistic image generation. In contrast to traditional GAN models, our SPGAN is able to dynamically adjust the size and architecture of a network in the training stage, by using the proposed selfgrowing and pruning mechanisms. To be more specific, we first train two seed networks as the generator and discriminator, each only contains a small number of convolution kernels. Such small-scale networks are much easier and faster to train than large-capacity networks. Second, in the self-growing step,we replicate the convolution kernels of each seed network to augment the scale of the network, followed by fine-tuning the augmented/expanded network. More importantly, to prevent the excessive growth of each seed network in the self-growing stage, we propose a pruning strategy that reduces the redundancy of an augmented network, yielding the optimal scale of the network. Last, we design a new adaptive loss function that is treated as a variable loss computational process for the training of the proposed SP-GAN model. By design, the hyperparameters of the loss function can dynamically adapt to different training stages. Experimental results obtained on a set of datasets demonstrate the merits of the proposed method, especially in terms of the stability and efficiency of network training. The source code of the proposed SP-GAN method is publicly available at

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Computer Science
Authors :
Song, Xiaoning
Chen, Yao
Hu, Guosheng
Yu, Dong-Jun
Wu, Xiao-Jun
Date : 21 June 2020
Funders : National Key Research and Development Program of China, National Natural Science Foundation of China, EPSRC, China Postdoctoral Science Foundation
Grant Title : National Key Research and Development Program of China Grant
Additional Information : Embargo OK Metadata Pending
Depositing User : James Marshall
Date Deposited : 22 Jun 2020 09:38
Last Modified : 22 Jun 2020 14:46

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800