中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Multi-scale conditional reconstruction generative adversarial network

文献类型：期刊论文

作者Chen, Yanming3; Xu, Jiahao3; An, Zhulin2; Zhuang, Fuzhen1
刊名IMAGE AND VISION COMPUTING
出版日期2024
卷号141页码:9
关键词Generative adversarial network Unsupervised generation Multi-scale instance Reconstructed losses
ISSN号0262-8856
DOI10.1016/j.imavis.2023.104885
英文摘要Generative adversarial network has become the factual standard for high-quality image synthesis. However, modeling the distribution of complex datasets (e.g. ImageNet and COCO-Stuff) remains challenging in unsupervised approaches. This is partly due to the imbalance between the generator and the discriminator during training, the discriminator easily defeats the generator because of special views. In this paper, we propose a model called multi-scale conditional reconstruction GAN (MS-GAN). The core concept of MS-GAN is to model the local density implicitly using different scales of instance conditions. Instance conditions are extracted from the target images via a self-supervised learning model. In addition, we alignment the semantic features of the observed instances by adding an additional reconstruction loss to the generator. Our MS-GAN can aggregate instance features at different scales and maximize semantic features. This allows the generator to learn additional comparative knowledge from instance features, leading to a better feature representation, thus improving the performance of the generation task. Experimental results on the ImageNet dataset and the COCO-Stuff dataset show that our method matches or exceeds the original performance in both FID and IS scores compared to the ICGAN framework. Additionally, our precision score on the ImageNet dataset improved from 74.2% to 79.9%.
资助项目National Science Foundation of China (NSFC)[62262067] ; Key Natural Science Foundation of Education Department of Anhui[KJ2021A0046]
WOS研究方向Computer Science ; Engineering ; Optics
语种英语
WOS记录号WOS:001145154200001
出版者ELSEVIER
源URL[http://119.78.100.204/handle/2XEOYT63/38411]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者An, Zhulin
作者单位1.Beihang Univ, Inst Artificial Intelligence, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
3.Anhui Univ, Sch Compute Sci & Technol, Hefei, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Yanming,Xu, Jiahao,An, Zhulin,et al. Multi-scale conditional reconstruction generative adversarial network[J]. IMAGE AND VISION COMPUTING,2024,141:9.
APA Chen, Yanming,Xu, Jiahao,An, Zhulin,&Zhuang, Fuzhen.(2024).Multi-scale conditional reconstruction generative adversarial network.IMAGE AND VISION COMPUTING,141,9.
MLA Chen, Yanming,et al."Multi-scale conditional reconstruction generative adversarial network".IMAGE AND VISION COMPUTING 141(2024):9.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。