Zobrazit v EDS

Center-push loss for joint view-based 3D model classification and retrieval feature learning.

Uloženo v:
Podrobná bibliografie
Název: Center-push loss for joint view-based 3D model classification and retrieval feature learning.
Autoři: Wang, Dong, Wang, Bin, Yao, Hongxun, Liu, Hong
Zdroj: Signal, Image & Video Processing; Jun2023, Vol. 17 Issue 4, p873-880, 8p
Abstrakt: View-based 3D model classification and retrieval are increasingly important in various fields. High classification accuracy and retrieval precision are urgently needed in the related applications. However, these two topics are always considered separately and very few works give an in-depth analysis of their relations. We would like to argue that although the classification and retrieval focus on different characteristics of embedding features, they are compatible rather than opposed to each other. Inspired by the recent deep metric learning approaches in this field, we propose a novelty loss named center-push loss for joint feature learning. The proposed loss can drive the convolutional neural network to learn object features that distributed compact in intra-class while separated in inter-class effectively. It avoids the annoying triplet sampling operation which always needs a delicately designed sampling strategy for efficient network optimization. The new loss is simple in structure and fast in training and achieves the best performance in classification and retrieval compared with many states of the arts. [ABSTRACT FROM AUTHOR]
Copyright of Signal, Image & Video Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáze: Complementary Index
Popis
Abstrakt:View-based 3D model classification and retrieval are increasingly important in various fields. High classification accuracy and retrieval precision are urgently needed in the related applications. However, these two topics are always considered separately and very few works give an in-depth analysis of their relations. We would like to argue that although the classification and retrieval focus on different characteristics of embedding features, they are compatible rather than opposed to each other. Inspired by the recent deep metric learning approaches in this field, we propose a novelty loss named center-push loss for joint feature learning. The proposed loss can drive the convolutional neural network to learn object features that distributed compact in intra-class while separated in inter-class effectively. It avoids the annoying triplet sampling operation which always needs a delicately designed sampling strategy for efficient network optimization. The new loss is simple in structure and fast in training and achieves the best performance in classification and retrieval compared with many states of the arts. [ABSTRACT FROM AUTHOR]
ISSN:18631703
DOI:10.1007/s11760-021-01923-4