• Home
  • Search
  • Channel-spatial attention modules in convolutional neural networks for image classification
  • Cite Icon2
  • https://doi.org/10.1038/s41598-025-32055-1Copy DOI Icon

Channel-spatial attention modules in convolutional neural networks for image classification

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Many studies have established that the attention mechanism has great potential in improving the performance of Convolutional Neural Networks (CNNs) in image classification problems in recent years. Combining channel and spatial attention modules is one of the different kinds of attention mechanisms that are inspired by the visual perception of the human brain. So far, no paper has considered both parallel and sequential states of combining channel-spatial attention modules, so that while comparing them comprehensively and accurately, it can be definitively said which of them is more optimal in terms of a better balance between efficiency and computational complexity of the model. In this paper, we introduced two new types of channel-spatial attention modules, the Parallel Channel-spatial Attention Module (PCSAM) and the Sequential Channel-spatial Attention Module (SCSAM), to embed in the architecture of any CNN. Each of the proposed attention modules is composed of a channel and spatial attention sub-modules. The Channel Attention Module (CAM) and Spatial Attention Module (SAM) help the network in extracting the channels related to the architecture of the Region of Interest (RoI) and its location in the input feature maps, respectively. We increase the representation power of the attention-based networks by extracting the features using Global Average Pooling (GAP) and Global Maximum Pooling (GMP) in the CAM and SAM. Also, the Dilation Convolution (DC) layer is employed in the structure of the SAM instead of the standard convolution to better focus on the RoI in the feature maps. The PCSAM and SCSAM are implemented in the architecture of the ResNet18 and MobileNetv4 to produce the ResNet18PCSAM, ResNet18SCSAM, MobileNetv4PCSAM, and MobileNetv4SCSAM. All networks are trained and evaluated on three general image classification datasets, the CIFAR-10, CIFAR-100, and Tiny-ImageNet, with the same experimental conditions for 50 epochs. The classification results in the test step show that the MobileNetv4SCSAM has a better efficiency than other architectures on all datasets. It also achieved higher performance than the previous existing channel-spatial attention modules.

Similar Papers
  • PDF
  • Research Article
  • Citations36

One Spatio-Temporal Sharpening Attention Mechanism for Light-Weight YOLO Models Based on Sharpening Spatial Attention

  • Nov 28, 2021
  • Sensors (Basel, Switzerland)
  • Mengfan Xue +4
  • Research Article
  • Citations1

Super-resolution reconstruction of binocular image based on multi-level fusion attention network

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Xu Lei +2
  • Research Article
  • Citations36

SAR Target Recognition Based on Efficient Fully Convolutional Attention Block CNN

  • Nov 25, 2020
  • IEEE Geoscience and Remote Sensing Letters
  • Rui Li +4
  • Conference Article
  • Citations4

3D Residual Networks with Channel-Spatial Attention Module for Action Recognition

  • Nov 06, 2020
  • Ziwen Yi +3
  • Research Article
  • Citations9

FAM: focal attention module for lesion segmentation of COVID-19 CT images.

  • Sep 04, 2022
  • Journal of real-time image processing
  • Xiaoxin Wu +8
  • Conference Article
  • Citations4

Automatic Detection of Ocean Eddy based on Deep Learning Technique with Attention Mechanism

  • May 24, 2022
  • Shaik John Saida +1
  • Conference Article

Efficient High-Resolution Network for Human Pose Estimation

  • Aug 17, 2022
  • Tien-Dat Tran +3
  • Research Article
  • Citations13

Large-Scale Image Retrieval with Deep Attentive Global Features.

  • Feb 25, 2023
  • International Journal of Neural Systems
  • Yingying Zhu +4
  • PDF
  • Research Article
  • Citations19

A Symmetric Efficient Spatial and Channel Attention (ESCA) Module Based on Convolutional Neural Networks

  • Jul 25, 2024
  • Symmetry
  • Huaiyu Liu +2
  • Research Article
  • Citations4

Attention graph: Learning effective visual features for large-scale image classification

  • Jan 01, 2022
  • Journal of Algorithms & Computational Technology
  • Xuelian Cui +4
  • Research Article
  • Citations1

HLAE-Net: A Hierarchical Lightweight Attention-Enhanced Strategy for Remote Sensing Scene Image Classification

  • Sep 24, 2025
  • Remote Sensing
  • Mingyuan Yang +5
  • Research Article
  • Citations29

Case instance segmentation of small farmland based on Mask R-CNN of feature pyramid network with double attention mechanism in high resolution satellite images

  • Jul 26, 2023
  • Computers and Electronics in Agriculture
  • Yangyang Cao +6
  • PDF
  • Research Article
  • Citations26

A Cloud Detection Method Using Convolutional Neural Network Based on Gabor Transform and Attention Mechanism with Dark Channel Subnet for Remote Sensing Image

  • Oct 07, 2020
  • Remote Sensing
  • Jing Zhang +7
  • PDF
  • Research Article
  • Citations92

CSA-MSO3DCNN: Multiscale Octave 3D CNN with Channel and Spatial Attention for Hyperspectral Image Classification

  • Jan 05, 2020
  • Remote Sensing
  • Qin Xu +3
  • Conference Article
  • Citations1

Lip-Reading Research Based on ShuffleNet and Attention-GRU

  • Jan 01, 2023
  • AHFE international
  • Yixian Fu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.