CSpace  > 中国科学院计算技术研究所期刊论文  > 英文
PIC: Domain generalization by path information constraint
Zhu, Jilong1,2; Zhuo, Junbao3; Wang, Shuhui1
2025-12-01
发表期刊PATTERN RECOGNITION
ISSN0031-3203
卷号168页码:12
摘要Despite the widespread use of deep neural networks in various tasks, their weak generalization ability to out-of-distribution data has always been one of the challenges hindering their practical applications. Domain Generalization (DG) aims to address this issue by learning domain-robust features across source domains, enabling models to generalize well to unseen target domains. Although DG has received extensive attention, existing solutions often overlook the relationships between different source domains and fail to make good utilization of the information contained in the source domain data to enhance the model's generalization ability. In this paper, we propose the Path Information Constraint (PIC) method, which enhances training diversity by constructing distinct learning paths within source domains and leverages constraints between paths to capture consistent and generalizable features. Experimental results show that our method achieves competitive results on multiple challenging benchmarks. PIC outperforms the best non-ensembled method by an average of 0.7% across four benchmarks, especially a 3.3% improvement on the OfficeHome benchmark. Furthermore, ensembling PIC by averaging multiple independently trained models leads to further improvements. The code is available at: https://github.com/JilongZhu/path_information_constraint.
关键词Domain generalization Transfer learning Path information constraint Adversarial manifold learning
DOI10.1016/j.patcog.2025.111769
收录类别SCI
语种英语
资助项目National Key R&D Program of China[2023YFC2508704] ; National Natural Science Foundation of China[62022083] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[62402033]
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:001501491400001
出版者ELSEVIER SCI LTD
引用统计
文献类型期刊论文
条目标识符http://119.78.100.204/handle/2XEOYT63/42318
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhuo, Junbao
作者单位1.Chinese Acad Sci, Inst Comput Tech, Key Lab Intell Info Proc, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Univ Sci & Technol Beijing, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Zhu, Jilong,Zhuo, Junbao,Wang, Shuhui. PIC: Domain generalization by path information constraint[J]. PATTERN RECOGNITION,2025,168:12.
APA Zhu, Jilong,Zhuo, Junbao,&Wang, Shuhui.(2025).PIC: Domain generalization by path information constraint.PATTERN RECOGNITION,168,12.
MLA Zhu, Jilong,et al."PIC: Domain generalization by path information constraint".PATTERN RECOGNITION 168(2025):12.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhu, Jilong]的文章
[Zhuo, Junbao]的文章
[Wang, Shuhui]的文章
百度学术
百度学术中相似的文章
[Zhu, Jilong]的文章
[Zhuo, Junbao]的文章
[Wang, Shuhui]的文章
必应学术
必应学术中相似的文章
[Zhu, Jilong]的文章
[Zhuo, Junbao]的文章
[Wang, Shuhui]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。