Loading [MathJax]/extensions/TeX/upgreek.js
Multiscale Representation Learning for Image Classification: A Survey | IEEE Journals & Magazine | IEEE Xplore

Multiscale Representation Learning for Image Classification: A Survey


Impact Statement:Multiscale representation learning techniques are fully utilized in existing artificial intelligence tasks. Compared to the existing papers, which pay attention to a part...Show More

Abstract:

Feature representation has been widely used and developed recently. Multiscale features have led to remarkable breakthroughs for representation learning process in many c...Show More
Impact Statement:
Multiscale representation learning techniques are fully utilized in existing artificial intelligence tasks. Compared to the existing papers, which pay attention to a particular task or algorithm, this paper is the first systematical review of multiscale representation learning in image classification tasks. Through comprehensive analysis, the basic principles and recent applications of multiscale geometric tools are analyzed more thoroughly. For multiscale networks, the proposed structural categories and design strategies are novel and complete in this paper. Meanwhile, the correlation between multiscale geometric analysis and multiscale networks is analyzed. The integration process and the characteristics of optimal representation are summarized to be benchmarks for future work. This paper can be a reasonable reference in the future exploration of multiscale representation learning, by giving the potential research directions in future work.

Abstract:

Feature representation has been widely used and developed recently. Multiscale features have led to remarkable breakthroughs for representation learning process in many computer vision tasks. This paper aims to provide a comprehensive survey of the recent multiscale representation learning achievements in classification tasks. Multiscale representation learning methods can be divided into two broad categories (multiscale geometric analysis and multiscale networks). Eleven kinds of multiscale geometric tools and seven kinds of multiscale networks are introduced. Some corresponding fundamental subproblems of these two broad categories are also described, including some concepts in representation process, specific representation methods with multiscale geometric analysis, and multiscale representation design strategies for networks. Then, the correlation between these two broad categories is illustrated, including respective characteristics, combination strategies, and characteristics of ...
Published in: IEEE Transactions on Artificial Intelligence ( Volume: 4, Issue: 1, February 2023)
Page(s): 23 - 43
Date of Publication: 14 December 2021
Electronic ISSN: 2691-4581

Funding Agency:


References

References is not available for this document.