1079
Views
176
Downloads
3
Crossref
N/A
WoS
N/A
Scopus
N/A
CSCD
Generative adversarial networks (GANs) are an unsupervised generative model that learns data distribution through adversarial training. However, recent experiments indicated that GANs are difficult to train due to the requirement of optimization in the high dimensional parameter space and the zero gradient problem. In this work, we propose a self-sparse generative adversarial network (Self-Sparse GAN) that reduces the parameter space and alleviates the zero gradient problem. In the Self-Sparse GAN, we design a self-adaptive sparse transform module (SASTM) comprising the sparsity decomposition and feature-map recombination, which can be applied on multi-channel feature maps to obtain sparse feature maps. The key idea of Self-Sparse GAN is to add the SASTM following every deconvolution layer in the generator, which can adaptively reduce the parameter space by utilizing the sparsity in multi-channel feature maps. We theoretically prove that the SASTM can not only reduce the search space of the convolution kernel weight of the generator but also alleviate the zero gradient problem by maintaining meaningful features in the batch normalization layer and driving the weight of deconvolution layers away from being negative. The experimental results show that our method achieves the best Fréchet inception distance (FID) scores for image generation compared with Wasserstein GAN with gradient penalty (WGAN-GP) on MNIST, Fashion-MNIST, CIFAR-10, STL-10, mini-ImageNet, CELEBA-HQ, and LSUN bedrooms datasets, and the relative decrease of FID is 4.76%–21.84%. Meanwhile, an architectural sketch dataset (Sketch) is also used to validate the superiority of the proposed method.
Generative adversarial networks (GANs) are an unsupervised generative model that learns data distribution through adversarial training. However, recent experiments indicated that GANs are difficult to train due to the requirement of optimization in the high dimensional parameter space and the zero gradient problem. In this work, we propose a self-sparse generative adversarial network (Self-Sparse GAN) that reduces the parameter space and alleviates the zero gradient problem. In the Self-Sparse GAN, we design a self-adaptive sparse transform module (SASTM) comprising the sparsity decomposition and feature-map recombination, which can be applied on multi-channel feature maps to obtain sparse feature maps. The key idea of Self-Sparse GAN is to add the SASTM following every deconvolution layer in the generator, which can adaptively reduce the parameter space by utilizing the sparsity in multi-channel feature maps. We theoretically prove that the SASTM can not only reduce the search space of the convolution kernel weight of the generator but also alleviate the zero gradient problem by maintaining meaningful features in the batch normalization layer and driving the weight of deconvolution layers away from being negative. The experimental results show that our method achieves the best Fréchet inception distance (FID) scores for image generation compared with Wasserstein GAN with gradient penalty (WGAN-GP) on MNIST, Fashion-MNIST, CIFAR-10, STL-10, mini-ImageNet, CELEBA-HQ, and LSUN bedrooms datasets, and the relative decrease of FID is 4.76%–21.84%. Meanwhile, an architectural sketch dataset (Sketch) is also used to validate the superiority of the proposed method.
L. Deng, The MNIST database of handwritten digit images for machine learning research [best of the web], IEEE Signal Process. Mag., vol. 29, no. 6, pp. 141–142, 2012.
F. Liu, L. Jiao, and X. Tang, Task-oriented GAN for PolSAR image classification and clustering, IEEE Trans. Neural Netw. Learn. Syst., vol. 30, no. 9, pp. 2707–2719, 2019.
R. Shang, W. Zhang, M. Lu, L. Jiao, and Y. Li, Feature selection based on non-negative spectral feature learning and adaptive rank constraint, Knowl. -Based Syst., vol. 236, p. 107749, 2022.
R. Shang, X. Zhang, J. Feng, Y. Li, and L. Jiao, Sparse and low-dimensional representation with maximum entropy adaptive graph for feature selection, Neurocomputing, vol. 485, pp. 57–73, 2022.
W. Qian, Y. Xu, and H. Li, A self-sparse generative adversarial network for autonomous early-stage design of architectural sketches, Comput. -Aided Civ. Infrastruct. Eng., vol. 37, no. 5, pp. 612–628, 2021.
This work was supported by the National Natural Science Foundation of China (Nos. 51921006 and 52008138), and Heilongjiang Touyan Innovation Team Program (No. AUEA5640200320).
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).