Back to Search
Start Over
判别增强的生成对抗模型在文本至图像生成中的研究与应用.
- Source :
-
Computer Engineering & Science / Jisuanji Gongcheng yu Kexue . May2022, Vol. 44 Issue 5, p855-861. 7p. - Publication Year :
- 2022
-
Abstract
- Based on Generative Adversarial Networks (GANs), most current text-to-image generation algorithms focus on designing different attention generation models to improve the characterization and expression of image details. However, they ignore the discriminator􀆳s perception of key local semantics, so the generation models can easily generate poor image details to "fool" the discriminators. This paper designs a vocabulary-image discriminative attention module in the discriminators to enhance the discriminators􀆳 ability to perceive and capture key semantics, and drive the generation model to generate high-quality image details. Therefore, a discrimination-enhanced generative adversarial model (DE-GAN) is proposed. The experimental results show that, on the CUB-Bird dataset, DE-GAN achieves 4.70 on the IS index, which is 4.2% higher than the baseline model and achieves high performance. [ABSTRACT FROM AUTHOR]
Details
- Language :
- Chinese
- ISSN :
- 1007130X
- Volume :
- 44
- Issue :
- 5
- Database :
- Academic Search Index
- Journal :
- Computer Engineering & Science / Jisuanji Gongcheng yu Kexue
- Publication Type :
- Academic Journal
- Accession number :
- 157428793
- Full Text :
- https://doi.org/10.3969/j.issn.1007-130X.2022.05.011