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
Hierarchical image-to-image translation with nested distributions modeling

文献类型：期刊论文

作者Qiao, Shishi1,2,3; Wang, Ruiping1,2; Shan, Shiguang1,2; Chen, Xilin1,2
刊名PATTERN RECOGNITION
出版日期2024-02-01
卷号146页码:12
关键词Image-to-image translation Distribution modeling Information entropy Generative adversarial network
ISSN号0031-3203
DOI10.1016/j.patcog.2023.110058
英文摘要Unpaired image-to-image translation among category domains has achieved remarkable success in past decades. Recent studies mainly focus on two challenges. For one thing, such translation is inherently multi-modal (i.e. many-to-many mapping) due to variations of domain-specific information (e.g., the domain of house cat contains multiple sub-modes), which is usually addressed by predefined distribution sampling. For another, most existing multi-modal approaches have limits in handling more than two domains with one model, i.e. they have to independently build two distributions to capture variations for every pair of domains. To address these problems, we propose a Hierarchical Image-to-image Translation (HIT) method which jointly formulates the multi-domain and multi-modal problem in a semantic hierarchy structure by modeling a common and nested distribution space. Specifically, domains have inclusion relationships under a particular hierarchy structure. With the assumption of Gaussian prior for domains, distributions of domains at lower levels capture the local variations of their ancestors at higher levels, leading to the so-called nested distributions. To this end, we propose a nested distribution loss in light of the distribution divergence measurement and information entropy theory to characterize the aforementioned inclusion relations among domain distributions. Experiments on ImageNet, ShapeNet, and CelebA datasets validate the promising results of our HIT against state-of-the-arts, and as additional benefits of nested modeling, one can even control the uncertainty of multi-modal translations at different hierarchy levels.
资助项目National Key R&D Program of China[2021ZD0111901] ; Natural Science Foundation of China[U21B2025] ; Natural Science Foundation of China[U19B2036] ; Natural Science Foundation of China[62206260]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001102929200001
出版者ELSEVIER SCI LTD
源URL[http://119.78.100.204/handle/2XEOYT63/38089]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Wang, Ruiping
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
3.Ocean Univ China, Coll Informat Sci & Engn, Qingdao 266100, Peoples R China
推荐引用方式
GB/T 7714		 Qiao, Shishi,Wang, Ruiping,Shan, Shiguang,et al. Hierarchical image-to-image translation with nested distributions modeling[J]. PATTERN RECOGNITION,2024,146:12.
APA Qiao, Shishi,Wang, Ruiping,Shan, Shiguang,&Chen, Xilin.(2024).Hierarchical image-to-image translation with nested distributions modeling.PATTERN RECOGNITION,146,12.
MLA Qiao, Shishi,et al."Hierarchical image-to-image translation with nested distributions modeling".PATTERN RECOGNITION 146(2024):12.

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。