SF-GAN: Semantic fusion generative adversarial networks for text-to-image synthesis

IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Expert Systems with Applications Pub Date : 2024-10-29 DOI:10.1016/j.eswa.2024.125583
Bing Yang , Xueqin Xiang , Wanzeng Kong , Jianhai Zhang , Jinliang Yao
{"title":"SF-GAN: Semantic fusion generative adversarial networks for text-to-image synthesis","authors":"Bing Yang ,&nbsp;Xueqin Xiang ,&nbsp;Wanzeng Kong ,&nbsp;Jianhai Zhang ,&nbsp;Jinliang Yao","doi":"10.1016/j.eswa.2024.125583","DOIUrl":null,"url":null,"abstract":"<div><div>Text-to-image synthesis aims to generate high-quality realistic images conditioned on text description. The major challenge of this task rests on the deep and seamless integration of text and image features. Therefore, in this paper, we present a novel approach, e.g., semantic fusion generative adversarial networks (SF-GAN), for fine-grained text-to-image generation, which enables efficient semantic interactions. Specifically, our proposed SF-GAN leverages a novel recurrent semantic fusion network to seamlessly manipulate the global allocation of text information across discrete fusion blocks. Moreover, with the usage of the contrastive loss and the dynamic convolution, SF-GAN could fuse the text and image information more accurately and further improve the semantic consistency in the generate stage. During the discrimination stage, we introduce a word-level discriminator designed to offer the generator precise feedback pertaining to each individual word. When compared to current state-of-the-art techniques, our SF-GAN demonstrates remarkable efficiency in generating realistic and text-aligned images, outperforming its contemporaries on challenging benchmark datasets.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":null,"pages":null},"PeriodicalIF":7.5000,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Expert Systems with Applications","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0957417424024503","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Text-to-image synthesis aims to generate high-quality realistic images conditioned on text description. The major challenge of this task rests on the deep and seamless integration of text and image features. Therefore, in this paper, we present a novel approach, e.g., semantic fusion generative adversarial networks (SF-GAN), for fine-grained text-to-image generation, which enables efficient semantic interactions. Specifically, our proposed SF-GAN leverages a novel recurrent semantic fusion network to seamlessly manipulate the global allocation of text information across discrete fusion blocks. Moreover, with the usage of the contrastive loss and the dynamic convolution, SF-GAN could fuse the text and image information more accurately and further improve the semantic consistency in the generate stage. During the discrimination stage, we introduce a word-level discriminator designed to offer the generator precise feedback pertaining to each individual word. When compared to current state-of-the-art techniques, our SF-GAN demonstrates remarkable efficiency in generating realistic and text-aligned images, outperforming its contemporaries on challenging benchmark datasets.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
SF-GAN:用于文本到图像合成的语义融合生成对抗网络
文本到图像的合成旨在根据文本描述生成高质量的逼真图像。这项任务的主要挑战在于如何深入、无缝地整合文本和图像特征。因此,在本文中,我们提出了一种新方法,如语义融合生成对抗网络(SF-GAN),用于细粒度文本到图像的生成,从而实现高效的语义交互。具体来说,我们提出的 SF-GAN 利用新颖的递归语义融合网络,在离散融合块之间无缝操作文本信息的全局分配。此外,通过使用对比损失和动态卷积,SF-GAN 可以更准确地融合文本和图像信息,进一步提高生成阶段的语义一致性。在判别阶段,我们引入了词级判别器,旨在为生成器提供与每个单词相关的精确反馈。与目前最先进的技术相比,我们的 SF-GAN 在生成逼真的文本对齐图像方面表现出了卓越的效率,在具有挑战性的基准数据集上,我们的 SF-GAN 优于同类技术。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Expert Systems with Applications
Expert Systems with Applications 工程技术-工程:电子与电气
CiteScore
13.80
自引率
10.60%
发文量
2045
审稿时长
8.7 months
期刊介绍: Expert Systems With Applications is an international journal dedicated to the exchange of information on expert and intelligent systems used globally in industry, government, and universities. The journal emphasizes original papers covering the design, development, testing, implementation, and management of these systems, offering practical guidelines. It spans various sectors such as finance, engineering, marketing, law, project management, information management, medicine, and more. The journal also welcomes papers on multi-agent systems, knowledge management, neural networks, knowledge discovery, data mining, and other related areas, excluding applications to military/defense systems.
期刊最新文献
Research on the generation and evaluation of bridge defect datasets for underwater environments utilizing CycleGAN networks Hybrid genetic algorithm with Wiener process for multi-scale colored balanced traveling salesman problem CE-DCVSI: Multimodal relational extraction based on collaborative enhancement of dual-channel visual semantic information Learning face super-resolution through identity features and distilling facial prior knowledge Identification of gene regulatory networks associated with breast cancer patient survival using an interpretable deep neural network model
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1