面向对象变形的定向生成对抗网络

Zhen Luo, Yingfang Zhang, Pei Zhong, Jingjing Chen, Donglong Chen
{"title":"面向对象变形的定向生成对抗网络","authors":"Zhen Luo, Yingfang Zhang, Pei Zhong, Jingjing Chen, Donglong Chen","doi":"10.1145/3512527.3531400","DOIUrl":null,"url":null,"abstract":"The concept of cycle consistency in couple mapping has helped CycleGAN illustrate remarkable performance in the context of image-to-image translation. However, its limitations in object transfiguration have not been ideally solved yet. In order to alleviate previous problems of wrong transformation position, degeneration, and artifacts, this work presents a new approach called Directional Generative Adversarial Network (DiGAN) in the field of object transfiguration. The major contribution of this work is threefold. First, paired directional generators are designed for both intra-domain and inter-domain generations. Second, a segmentation network based on Mask R-CNN is introduced to build conditional inputs for both generators and discriminators. Third, a feature loss and a segmentation loss are added to optimize the model. Experimental results indicate that DiGAN surpasses CycleGAN and AttentionGAN by 17.2% and 60.9% higher on Inception Score, 15.5% and 2.05% lower on Fréchet Inception Distance, and 14.2% and 15.6% lower on VGG distance, respectively, in horse-to-zebra mapping.","PeriodicalId":179895,"journal":{"name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DiGAN: Directional Generative Adversarial Network for Object Transfiguration\",\"authors\":\"Zhen Luo, Yingfang Zhang, Pei Zhong, Jingjing Chen, Donglong Chen\",\"doi\":\"10.1145/3512527.3531400\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The concept of cycle consistency in couple mapping has helped CycleGAN illustrate remarkable performance in the context of image-to-image translation. However, its limitations in object transfiguration have not been ideally solved yet. In order to alleviate previous problems of wrong transformation position, degeneration, and artifacts, this work presents a new approach called Directional Generative Adversarial Network (DiGAN) in the field of object transfiguration. The major contribution of this work is threefold. First, paired directional generators are designed for both intra-domain and inter-domain generations. Second, a segmentation network based on Mask R-CNN is introduced to build conditional inputs for both generators and discriminators. Third, a feature loss and a segmentation loss are added to optimize the model. Experimental results indicate that DiGAN surpasses CycleGAN and AttentionGAN by 17.2% and 60.9% higher on Inception Score, 15.5% and 2.05% lower on Fréchet Inception Distance, and 14.2% and 15.6% lower on VGG distance, respectively, in horse-to-zebra mapping.\",\"PeriodicalId\":179895,\"journal\":{\"name\":\"Proceedings of the 2022 International Conference on Multimedia Retrieval\",\"volume\":\"8 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-06-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2022 International Conference on Multimedia Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3512527.3531400\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2022 International Conference on Multimedia Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3512527.3531400","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

耦合映射中的循环一致性概念帮助CycleGAN在图像到图像的翻译中展示了卓越的性能。然而,它在对象变形方面的局限性还没有得到理想的解决。为了缓解以往变换位置错误、退化和伪影等问题,本文在对象变换领域提出了一种新的方法——定向生成对抗网络(DiGAN)。这项工作的主要贡献有三个方面。首先,设计了域内和域间生成的成对方向生成器。其次,引入基于Mask R-CNN的分割网络,为生成器和鉴别器构建条件输入。第三,加入特征损失和分割损失对模型进行优化。实验结果表明,DiGAN在马-斑马映射的Inception Score上分别比CycleGAN和AttentionGAN高17.2%和60.9%,在fr盗梦距离上分别比CycleGAN和AttentionGAN低15.5%和2.05%,在VGG距离上分别比CycleGAN和AttentionGAN低14.2%和15.6%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
DiGAN: Directional Generative Adversarial Network for Object Transfiguration
The concept of cycle consistency in couple mapping has helped CycleGAN illustrate remarkable performance in the context of image-to-image translation. However, its limitations in object transfiguration have not been ideally solved yet. In order to alleviate previous problems of wrong transformation position, degeneration, and artifacts, this work presents a new approach called Directional Generative Adversarial Network (DiGAN) in the field of object transfiguration. The major contribution of this work is threefold. First, paired directional generators are designed for both intra-domain and inter-domain generations. Second, a segmentation network based on Mask R-CNN is introduced to build conditional inputs for both generators and discriminators. Third, a feature loss and a segmentation loss are added to optimize the model. Experimental results indicate that DiGAN surpasses CycleGAN and AttentionGAN by 17.2% and 60.9% higher on Inception Score, 15.5% and 2.05% lower on Fréchet Inception Distance, and 14.2% and 15.6% lower on VGG distance, respectively, in horse-to-zebra mapping.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信