• Home
  • Search
  • One Spatio-Temporal Sharpening Attention Mechanism for Light-Weight YOLO Models Based on Sharpening Spatial Attention
  • Cite Icon36
  • https://doi.org/10.3390/s21237949Copy DOI Icon

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

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Attention mechanisms have demonstrated great potential in improving the performance of deep convolutional neural networks (CNNs). However, many existing methods dedicate to developing channel or spatial attention modules for CNNs with lots of parameters, and complex attention modules inevitably affect the performance of CNNs. During our experiments of embedding Convolutional Block Attention Module (CBAM) in light-weight model YOLOv5s, CBAM does influence the speed and increase model complexity while reduce the average precision, but Squeeze-and-Excitation (SE) has a positive impact in the model as part of CBAM. To replace the spatial attention module in CBAM and offer a suitable scheme of channel and spatial attention modules, this paper proposes one Spatio-temporal Sharpening Attention Mechanism (SSAM), which sequentially infers intermediate maps along channel attention module and Sharpening Spatial Attention (SSA) module. By introducing sharpening filter in spatial attention module, we propose SSA module with low complexity. We try to find a scheme to combine our SSA module with SE module or Efficient Channel Attention (ECA) module and show best improvement in models such as YOLOv5s and YOLOv3-tiny. Therefore, we perform various replacement experiments and offer one best scheme that is to embed channel attention modules in backbone and neck of the model and integrate SSAM into YOLO head. We verify the positive effect of our SSAM on two general object detection datasets VOC2012 and MS COCO2017. One for obtaining a suitable scheme and the other for proving the versatility of our method in complex scenes. Experimental results on the two datasets show obvious promotion in terms of average precision and detection performance, which demonstrates the usefulness of our SSAM in light-weight YOLO models. Furthermore, visualization results also show the advantage of enhancing positioning ability with our SSAM.

Loading PDF

Similar Papers
  • 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
  • Conference Article
  • Citations4

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

  • Nov 06, 2020
  • Ziwen Yi +3
  • Conference Article
  • Citations1

Lip-Reading Research Based on ShuffleNet and Attention-GRU

  • Jan 01, 2023
  • AHFE international
  • Yixian Fu +1
  • Research Article
  • Citations197

A CBAM Based Multiscale Transformer Fusion Approach for Remote Sensing Image Change Detection

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Wei Wang +3
  • Research Article
  • Citations24

3D mineral prospectivity modeling in the Sanshandao goldfield, China using the convolutional neural network with attention mechanism

  • Dec 31, 2023
  • Ore Geology Reviews
  • Zhankun Liu +8
  • Research Article
  • Citations2

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

  • Dec 11, 2025
  • Scientific Reports
  • Mohammad Zolfaghari +2
  • Conference Article
  • Citations5

MEDA: Multi-output Encoder-Decoder for Spatial Attention in Convolutional Neural Networks

  • Nov 01, 2019
  • Huayu Li +1
  • Research Article
  • Citations4

An Improved Lightweight YOLO Algorithm for Recognition of GPS Interference Signals in Civil Aviation

  • Jan 01, 2024
  • IET Signal Processing
  • Mian Zhong +7
  • Research Article
  • Citations17

Improved faster region convolutional neural network algorithm for UAV target detection in complex environment

  • Jun 28, 2024
  • Results in Engineering
  • Gengyan Cui +1
  • Research Article
  • Citations30

Faster RCNN Target Detection Algorithm Integrating CBAM and FPN

  • Jun 07, 2023
  • Applied Sciences
  • Wenshun Sheng +3
  • PDF
  • Research Article
  • Citations77

Research on a U-Net Bridge Crack Identification and Feature-Calculation Methods Based on a CBAM Attention Mechanism

  • Sep 28, 2022
  • Buildings
  • Huifeng Su +5
  • Research Article
  • Citations18

Deep learning based weed classification in corn using improved attention mechanism empowered by Explainable AI techniques

  • Apr 01, 2025
  • Crop Protection
  • Akshay Dheeraj +1
  • Research Article
  • Citations2

Nondestructive Detection of Soluble Solids Content in Apples Based on Multi-Attention Convolutional Neural Network and Hyperspectral Imaging Technology.

  • Nov 09, 2025
  • Foods (Basel, Switzerland)
  • Yan Tian +5
  • Research Article
  • Citations1

Impact of shared dense connectivity and channel width on convolutional block attention module for regional MRI-based brain tumor classification

  • Oct 08, 2025
  • Biomedical Physics & Engineering Express
  • Binish M C +1
  • Research Article
  • Citations20

ICS-ResNet: A Lightweight Network for Maize Leaf Disease Classification

  • Jul 21, 2024
  • Agronomy
  • Zhengjie Ji +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.