GIU-GANs: Global Information Utilization for Generative Adversarial Networks

TL;DR

This paper introduces GIU-GANs, a novel GAN architecture that utilizes a Global Information Utilization module and Representative Batch Normalization to improve image quality by capturing global features and reducing overfitting.

Contribution

The paper proposes GIU-GANs with a new GIU module combining SENet and involution, and RBN, to enhance feature extraction and image quality in GANs.

Findings

Achieves state-of-the-art performance on CIFAR-10 and CelebA datasets.

Improves image detail and quality over traditional GANs.

Reduces overfitting through novel normalization techniques.

Abstract

In recent years, with the rapid development of artificial intelligence, image generation based on deep learning has dramatically advanced. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, since convolutions are limited by spatial-agnostic and channel-specific, features extracted by traditional GANs based on convolution are constrained. Therefore, GANs are unable to capture any more details per image. On the other hand, straightforwardly stacking of convolutions causes too many parameters and layers in GANs, which will lead to a high risk of overfitting. To overcome the aforementioned limitations, in this paper, we propose a new GANs called Involution Generative Adversarial Networks (GIU-GANs). GIU-GANs leverages a brand new module called the Global Information Utilization (GIU) module, which integrates Squeeze-and-Excitation Networks (SENet) and involution to focus on global information by channel attention mechanism, leading to a higher quality of generated images. Meanwhile, Batch Normalization(BN) inevitably ignores the representation differences among noise sampled by the generator, and thus degrade the generated image quality. Thus we introduce Representative Batch Normalization(RBN) to the GANs architecture for this issue. The CIFAR-10 and CelebA datasets are employed to demonstrate the effectiveness of our proposed model. A large number of experiments prove that our model achieves state-of-the-art competitive performance.