Geometry Flow-Based Deep Riemannian Metric Learning

doi:10.1109/JAS.2023.123399

CASIA OpenIR > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Geometry Flow-Based Deep Riemannian Metric Learning
	Yangyang Li; Chaoqun Fei; Chuanqing Wang; Hongming Shan; Ruqian Lu
发表期刊	IEEE/CAA Journal of Automatica Sinica
ISSN	2329-9266
	2023
卷号	10 期号:9 页码:1882-1892
摘要	Deep metric learning (DML) has achieved great results on visual understanding tasks by seamlessly integrating conventional metric learning with deep neural networks. Existing deep metric learning methods focus on designing pair-based distance loss to decrease intra-class distance while increasing inter-class distance. However, these methods fail to preserve the geometric structure of data in the embedding space, which leads to the spatial structure shift across mini-batches and may slow down the convergence of embedding learning. To alleviate these issues, by assuming that the input data is embedded in a lower-dimensional sub-manifold, we propose a novel deep Riemannian metric learning (DRML) framework that exploits the non-Euclidean geometric structural information. Considering that the curvature information of data measures how much the Riemannian (non-Euclidean) metric deviates from the Euclidean metric, we leverage geometry flow, which is called a geometric evolution equation, to characterize the relation between the Riemannian metric and its curvature. Our DRML not only regularizes the local neighborhoods connection of the embeddings at the hidden layer but also adapts the embeddings to preserve the geometric structure of the data. On several benchmark datasets, the proposed DRML outperforms all existing methods and these results demonstrate its effectiveness.
关键词	Curvature regularization deep metric learning (DML) embedding learning geometry flow riemannian metric
DOI	10.1109/JAS.2023.123399
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/52376
专题	学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Yangyang Li,Chaoqun Fei,Chuanqing Wang,et al. Geometry Flow-Based Deep Riemannian Metric Learning[J]. IEEE/CAA Journal of Automatica Sinica,2023,10(9):1882-1892.
APA	Yangyang Li,Chaoqun Fei,Chuanqing Wang,Hongming Shan,&Ruqian Lu.(2023).Geometry Flow-Based Deep Riemannian Metric Learning.IEEE/CAA Journal of Automatica Sinica,10(9),1882-1892.
MLA	Yangyang Li,et al."Geometry Flow-Based Deep Riemannian Metric Learning".IEEE/CAA Journal of Automatica Sinica 10.9(2023):1882-1892.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
JAS-2022-1151.pdf（1815KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载