TextControlGAN: Text-to-Image Synthesis with Controllable Generative Adversarial Networks

Author:

Ku Hyeeun1,Lee Minhyeok1ORCID

Affiliation:

1. School of Electrical and Electronics Engineering, Chung-Ang University, Seoul 06974, Republic of Korea

Abstract

Generative adversarial networks (GANs) have demonstrated remarkable potential in the realm of text-to-image synthesis. Nevertheless, conventional GANs employing conditional latent space interpolation and manifold interpolation (GAN-CLS-INT) encounter challenges in generating images that accurately reflect the given text descriptions. To overcome these limitations, we introduce TextControlGAN, a controllable GAN-based model specifically designed for text-to-image synthesis tasks. In contrast to traditional GANs, TextControlGAN incorporates a neural network structure, known as a regressor, to effectively learn features from conditional texts. To further enhance the learning performance of the regressor, data augmentation techniques are employed. As a result, the generator within TextControlGAN can learn conditional texts more effectively, leading to the production of images that more closely adhere to the textual conditions. Furthermore, by concentrating the discriminator’s training efforts on GAN training exclusively, the overall quality of the generated images is significantly improved. Evaluations conducted on the Caltech-UCSD Birds-200 (CUB) dataset demonstrate that TextControlGAN surpasses the performance of the cGAN-based GAN-INT-CLS model, achieving a 17.6% improvement in Inception Score (IS) and a 36.6% reduction in Fréchet Inception Distance (FID). In supplementary experiments utilizing 128 × 128 resolution images, TextControlGAN exhibits a remarkable ability to manipulate minor features of the generated bird images according to the given text descriptions. These findings highlight the potential of TextControlGAN as a powerful tool for generating high-quality, text-conditioned images, paving the way for future advancements in the field of text-to-image synthesis.

Funder

National Research Foundation of Korea

Publisher

MDPI AG

Subject

Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science

Reference53 articles.

1. Samek, W., Wiegand, T., and Müller, K.-R. (2017). Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv.

2. Lee, Y.-L., Tsung, P.-K., and Wu, M. (2018, January 16–19). Techology trend of edge ai. Proceedings of the 2018 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), Hsinchu, Taiwan.

3. Ongsulee, P. (2017, January 22–24). Artificial intelligence, machine learning and deep learning. Proceedings of the 2017 15th International Conference on ICT and Knowledge Engineering (ICT&KE), Bangkok, Thailand.

4. Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., and Frey, B. (2015). Adversarial autoencoders. arXiv.

5. Mescheder, L., Nowozin, S., and Geiger, A. (2017, January 6–11). Adversarial variational bayes: Unifying variational autoencoders and generative adversarial networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia.

Cited by 7 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3