Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Visual System01:26

Visual System

1.6K
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
1.6K
Neural Circuits01:25

Neural Circuits

2.6K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.6K
Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

1.7K
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
1.7K
Parallel Processing01:20

Parallel Processing

600
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
600
Association Areas of the Cortex01:21

Association Areas of the Cortex

8.7K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
8.7K
Vision01:24

Vision

59.2K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
59.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

NeXtSwin-X: dual-branch cross-attention fusion of ConvNeXt and swin transformer for accurate brain tumor classification from MRI and CT.

Scientific reports·2026
Same author

Design and development of a convolutional neural network based on human cognitive attention mechanism for automatic classification of leukemia.

PloS one·2026
Same author

Task-specific neural networks for medical imaging using pretrained fragments.

Computers in biology and medicine·2026
Same author

Alzheimer's disease prediction via an explainable CNN using genetic algorithm and SHAP values.

PloS one·2026
Same author

AI-driven approaches for dysgraphia diagnosis using online and offline handwriting data: A comprehensive scoping review.

PloS one·2025
Same author

Detection of retinal diseases using an accelerated reused convolutional network.

Computers in biology and medicine·2024

Related Experiment Video

Updated: Jan 8, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

991

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

Mohammad Zolfaghari1, Mohammad Saniee Abadeh2, Hedieh Sajedi3

  • 1Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran.

Scientific Reports
|December 11, 2025
PubMed
Summary

This study introduces novel Parallel and Sequential Channel-spatial Attention Modules (PCSAM and SCSAM) for Convolutional Neural Networks (CNNs). The Sequential Channel-spatial Attention Module (SCSAM) demonstrated superior efficiency and performance in image classification tasks.

Keywords:
Attention mechanismConvolutional neural networks (CNNs)Image classificationParallel channel-spatial attention module (PCSAM)Sequential channel-spatial attention module (SCSAM)

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

723
Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention
05:36

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Published on: November 16, 2017

7.9K

Related Experiment Videos

Last Updated: Jan 8, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

991
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

723
Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention
05:36

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Published on: November 16, 2017

7.9K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Attention mechanisms enhance Convolutional Neural Networks (CNNs) for image classification.
  • Channel and spatial attention modules, inspired by human visual perception, are key components.
  • Previous research has not comprehensively compared parallel and sequential combinations of these modules.

Purpose of the Study:

  • To introduce and evaluate two novel channel-spatial attention modules: Parallel Channel-spatial Attention Module (PCSAM) and Sequential Channel-spatial Attention Module (SCSAM).
  • To investigate the optimal configuration of channel-spatial attention modules for balancing model efficiency and computational complexity.
  • To enhance the feature representation power of attention-based CNNs.

Main Methods:

  • Developed PCSAM and SCSAM, integrating Channel Attention Module (CAM) and Spatial Attention Module (SAM) sub-modules.
  • Utilized Global Average Pooling (GAP) and Global Maximum Pooling (GMP) within CAM and SAM for feature extraction.
  • Employed Dilation Convolution (DC) in SAM for improved Region of Interest (RoI) focus.
  • Integrated PCSAM and SCSAM into ResNet18 and MobileNetv4 architectures.
  • Trained and evaluated models on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets for 50 epochs.

Main Results:

  • The MobileNetv4SCSAM architecture achieved superior efficiency across all tested datasets.
  • MobileNetv4SCSAM demonstrated higher classification performance compared to other evaluated architectures.
  • The proposed SCSAM outperformed existing channel-spatial attention modules.

Conclusions:

  • The Sequential Channel-spatial Attention Module (SCSAM) offers an optimal balance between efficiency and computational complexity for CNNs.
  • SCSAM integration leads to significant improvements in image classification performance.
  • This work provides valuable insights into the effective combination of attention mechanisms in deep learning models.