GIU-GANs: Global Information Utilization for Generative Adversarial Networks. (August 2022)

• Record Type: Journal Article
• Authors: Tian, Yongqi; Gong, Xueyuan; Tang, Jialin; Su, Binghua; Liu, Xiaoxiang; Zhang, Xinyuan
• Is Part Of: Neural networks. Volume 152(2022)
• Page Start: 487
• Page End: 498
• Publication Date: 2022-08
• Subjects: Image generation -- Generative Adversarial Networks -- Global Information Utilization -- Involution -- Representative Batch Normalization; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2022.05.014
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Recently, with the rapid development of artificial intelligence, image generation based on deep learning has advanced significantly. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, because convolutions are limited by spatial-agnostic and channel-specific, features extracted by conventional GANs based on convolution are constrained. Therefore, GANs cannot capture in-depth details per image. Moreover, straightforwardly stacking of convolutions causes too many parameters and layers in GANs, yielding a high overfitting risk. To overcome the abovementioned limitations, in this study, we propose a GANs called GIU-GANs (where Global Information Utilization: GIU). GIU-GANs leverages a new module called the GIU module, which integrates the squeeze-and-excitation module and involution to focus on global information via the channel attention mechanism, enhancing the generated image quality. Moreover, Batch Normalization (BN) inevitably ignores the representation differences among noise sampled by the generator and thus degrades the generated image quality. Thus, we introduce the representative BN to the GANs' architecture. The CIFAR-10 and CelebA datasets are employed to demonstrate the effectiveness of the proposed model. Numerous experiments indicate that the proposed model achieves state-of-the-art performance.