Spatial Global Context Attention for Convolutional Neural Networks: An Efficient Method

Yang Yu, Yi Zhang, Xingxing Zhu, Zeyu Cheng, Zhe Song, Chengkai Tang

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Capturing global contextual information within an image can significantly enhance visual understanding. However, current attention methods model long-range dependencies between features by aggregating query-specific global context to each query position. These methods are inefficient and consume a huge amount of memory and computational resources, making them less practical. To address this issue, we propose a simple, low-cost, and high-performance Spatial Global Context Attention (SGCA) module. This module aggregates query-independent global context to update features at each query position, capturing spatial global contextual information in an efficient and effective manner, significantly improving feature representations, which contributes to more precise classification results. The proposed SGCA is lightweight and flexible, making it suitable as an independent add-on component that can be applied to various convolutional neural networks (CNNs) to create a family of new architectures named SGCANet. Without bells and whistles, extensive experimental results on CIFAR-100 and ImageNet-1K for image recognition tasks demonstrate that our method significantly outperforms other counterparts in classification performance at a cheaper cost, achieving leading results.

源语言英语
主期刊名2024 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2024
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9798350366556
DOI
出版状态已出版 - 2024
活动14th IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2024 - Hybrid, Bali, 印度尼西亚
期限: 19 8月 202422 8月 2024

出版系列

姓名2024 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2024

会议

会议14th IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2024
国家/地区印度尼西亚
Hybrid, Bali
时期19/08/2422/08/24

指纹

探究 'Spatial Global Context Attention for Convolutional Neural Networks: An Efficient Method' 的科研主题。它们共同构成独一无二的指纹。

引用此