Channel-Wise Correlation Calibrates Attention Module for Convolutional Neural Networks
| العنوان: | Channel-Wise Correlation Calibrates Attention Module for Convolutional Neural Networks |
|---|---|
| المؤلفون: | Ziqiang Lu, Yanwu Dong, Jie Li, Ziying Lu, Pengjie He, Haibo Ru |
| المصدر: | Journal of Sensors. 2022:1-10 |
| بيانات النشر: | Hindawi Limited, 2022. |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | Article Subject, Control and Systems Engineering, Electrical and Electronic Engineering, Instrumentation |
| الوصف: | It is well known in image recognition that global features represent the overall and have the ability to generalize an entire object, while local features can reflect the details, both of which are important for extracting more discriminative features. Recent research has shown that the performance of convolutional neural networks can be improved by introducing an attention module. In this paper, we propose a simple and effective channel attention module named layer feature that meets channel attention module (LC module, LCM), which combines the layer global information with channel dependence to calibrate the correlation between channel features and then adaptively recalibrates channel-wise feature responses. Compared with the traditional channel attention methods, the LC module utilizes the most significant information that needs to be focused on in the overall features to refine the channel relationship. Through empirical studies on CIFAR-10, CIFAR-100, and mini-ImageNet, this work proved its superiority compared to other attention modules in different DCNNs. Furthermore, we performed the two-dimensional visualization of the feature map through the class activation map and intuitively analyzed the effectiveness of the model. |
| وصف الملف: | text/xhtml |
| تدمد: | 1687-7268 1687-725X |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::747947944c4cff9c57d07df15b1a936b https://doi.org/10.1155/2022/2000170 |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi.dedup.....747947944c4cff9c57d07df15b1a936b |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 16877268 1687725X |
|---|