ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

GMF-GAN: Gradual multi-granularity semantic fusion GAN for text-to-image synthesis

Jin, Dehu; Li, Guangju; Yu, Qi; Yu, Lan; Cui, Jia*; Qi, Meng*shandong normal univ
Digital Signal Processing: A Review Journal2023-8DOI: 10.1016/j.dsp.2023.104105
11阅读
引用收藏
分享

摘要

Text-to-image Synthesis is to obtain images with both authenticity and semantic consistency from natural language descriptions. However, in previous methods, the fusion of semantic information during image generation is insufficient. The multi-stage model fuses semantic information of different granularities in different stages, so the semantic information is not fully utilized. The single-stage model only aims at fusing coarse-grained semantic information, ignoring the detailed information in fine-grained semantics. To this end, we propose a gradual multi-granularity semantic fusion GAN, which gradually fuses multigranularity semantic information into feature maps of different scales and realizes the full utilization of multi-granularity semantic information. GMF-GAN adopts two novel attention modules: Adaptive Sentence Attention Fusion (ASAF) module and Adaptive Word Attention Fusion (AWAF) module. The ASAF guides the generator to focus on sentence-related regional features, and adaptively fine-tunes feature maps via attention weights. The AWAF assigns greater weight to word-related regional features by modeling the importance of each word. We also propose a text-image consistency loss to ensure that the generated image is semantically consistent with the input text. Qualitative and quantitative experimental results on two benchmark datasets show that GMF-GAN outperforms the state-of-the-art models.& COPY; 2023 Elsevier Inc.

学科与关键词

关键词
Text-to-image synthesisCross-model information fusionAttention mechanismText-image consistency loss
相关
加载中…
  • Enhancing fine-detail image synthesis from text descriptions by text aggregation and connection fusion module
    Zhou, Huaping; Wu, Tao; Ye, Senmao; Qin, Xinru; Sun, Kelei*Signal Processing: Image Communication , 2024, 122: 117099.
  • Fine-Grained Cross-Modal Fusion Based Refinement for Text-to-Image Synthesis
    Haoran, Sun; Yang, Wang*; Haipeng, Liu; Biao, QianCHINESE JOURNAL OF ELECTRONICS, 2023, 32(6): 1329-1340.
  • CcGL-GAN: Criss-Cross Attention and Global-Local Discriminator Generative Adversarial Networks for text-to-image synthesis
    Ye, Xihong; Lu, Lu*International Joint Conference on Neural Networks (IJCNN), ELECTR NETWORK, 2021-07-18 To 2021-07-22.
查看全部 →

发表信息

论文状态
公开发表
期刊
Digital Signal Processing: A Review Journal
发表日期
2023-08
卷期
第 140 卷
页码
104105
DOI
10.1016/j.dsp.2023.104105
语言
ENGLISH
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61902225]; Natural Science Foundation of Shandong Province, China [ZR2021LZL011]

作者

  • J

    Jin, Dehu (第一作者)

    shandong normal univ

  • L

    Li, Guangju

    shandong normal univ

查看全部 6 位作者收起作者
  • Y

    Yu, Qi

    shandong normal univ

  • Y

    Yu, Lan

    shandong normal univ

  • C

    Cui, Jia (通讯)

  • Q

    Qi, Meng (通讯)

    shandong normal univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417