.png){kind=icon}
Return
Deep Metric Learning With Manifold Class Variability Analysis
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2021.3101944.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In deep metric learning (DML) techniques, understanding both the local and global characteristics of embedding space is essential. However, conventional DML techniques have two limitations as follows: First, Euclidean distance-based metrics never imply global information such as class variability because they only depend on the physical distance of samples. Second, they assume that the embedding space is simply a vector space which cannot represent complex data features. Therefore, we propose a novel loss function which can fully utilize characteristics of embedding space by using discriminant analysis and nonlinear mapping. With theoretical analysis, the superior performance of the proposed method is verified for the fine-grained retrieval datasets such as Cars196, CUB200-2011, Stanford online products, and In-shop clothes. Source code is available at https://github.com/kdhht2334/MCVA.
Keywords:
Measurement
Manifolds
Task analysis
Tools
Probability distribution
Neural networks
Extraterrestrial measurements
Deep metric learning
image retrieval
linear discriminant analysis
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
View more