Frequency Regulated Channel-Spatial Attention module for improved image classification

doi:10.1016/j.eswa.2024.125463

Frequency Regulated Channel-Spatial Attention module for improved image classification

2025-01-01

0

PRE

AI

DOI：10.1016/j.eswa.2024.125463

Original

Original request for help

Save

Abstract

En 中文

Convolutional neural networks play a vital role in image classification, with attention mechanisms enhancing discriminability on large datasets like ImageNet. However, challenges persist in optimizing performance for smaller or moderate real-world datasets due to limited data availability. There is a deficiency in effectively leveraging both channel and spatial attention for enhanced effectiveness in such scenarios. Although predefined filters offer advantages, their integration with attention mechanisms for complementary strength remains under-explored. In this paper, we propose the Frequency Regulated Channel-Spatial Attention (FReCSA) module to address this challenge by leveraging the power of channel attention and spatial attention. Four subsets and the complete ImageNet dataset, along with five additional datasets are used to evaluate FReCSA in our experiments. Integrating the FReCSA module into ResNet50 significantly enhances the top-1 accuracy, which is demonstrated by a 10.13% increase over the second-best on the ImageNet-40 dataset. On the other hand, our FReCSA module introduces minimal computational and parameter overhead to the deep network in terms of model size and computational operations, which makes FReCSA a good choice for learning tasks. The source code of this work is available at https://github.com/CoVIS-UNT/FReCSA.

Keywords:

Classification

Attention

Regularization

Filter

Frequency Regulated Channel-Spatial Attention module for improved image classification

Abstract

Journal

Organization