Dual Wavelet Attention Networks for Image Classification
IEEE Transactions on Circuits and Systems for Video Technology · 2023-04 · 33 (4) · 1899-1910
DOI: 10.1109/tcsvt.2022.3218735 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-04. Verfasst von Yuting Yang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 86-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Key Scientific Technological Innovation Research Project, Ministry of Education, State Key Program and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China.
Abstract (Originalsprache)
Global average pooling (GAP) plays an important role in traditional channel attention. However, there is the disadvantage of insufficient information to use the result of GAP as the channel scalar. At the same time, the existing spatial attention models focus on the areas of interest using average pooling or convolutional networks, but there is a loss of feature information and neglect of the structural feature. In this paper, dual wavelet attention is proposed, which can effectively alleviate the aforementioned problems and enhance the representation ability of CNNs. Firstly, the equivalence between the sum of the low-frequency subband coefficients of 2D DWT (Haar) and GAP is proved. On this basis, the statistical characteristics of low-frequency and high-frequency subbands are effectively combined to obtain the channel scalars, which can better measure the importance of each channel. In addition, 2D DWT can effectively capture the approximate and detailed structural features. Thus, wavelet spatial attention is proposed, which can effectively focus on the key spatial structural features. Different from traditional spatial attention, it can better curve the structural and spatial attention for different channels. The experiments are verified on four natural image data sets and three remote sensing scene classification data sets, which shows the effectiveness and versatility of the proposed methods. The code of this paper will be available at https://github.com/yutinyang/DWAN.
Förderung
- Key Scientific Technological Innovation Research Project
- Ministry of Education
- State Key Program and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China
- Key Research and Development Program in Shaanxi Province of China
- Major Research Plan of the National Natural Science Foundation of China
- National Natural Science Foundation of China
- Fund for Foreign Scholars in University Research and Teaching Program’s 111 Project
- Program for Cheung Kong Scholars and Innovative Research Team in University
Zitieren
APA
Yang, Y., Jiao, L., Liu, X., Liu, F., Yang, S., Li, L., Chen, P., Li, X., & Huang, Z. (2023). Dual Wavelet Attention Networks for Image Classification. IEEE Transactions on Circuits and Systems for Video Technology, 33(4), 1899-1910. https://doi.org/10.1109/tcsvt.2022.3218735
Vancouver
Yang Y, Jiao L, Liu X, Liu F, Yang S, Li L, et al. Dual Wavelet Attention Networks for Image Classification. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(4):1899-1910. doi:10.1109/tcsvt.2022.3218735
BibTeX
@article{Yang2023,
author = {Yang, Yuting and Jiao, Licheng and Liu, Xu and Liu, Fang and Yang, Shuyuan and Li, Lingling and Chen, Puhua and Li, Xiufang and Huang, Zhongjian},
title = {Dual Wavelet Attention Networks for Image Classification},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2023},
volume = {33},
number = {4},
pages = {1899--1910},
doi = {10.1109/tcsvt.2022.3218735}
}
EUVIMED