• Home
  • Search
  • A Multi-Domain Collaborative Transfer Learning Method with Multi-Scale Repeated Attention Mechanism for Underwater Side-Scan Sonar Image Classification
  • Open Access IconOpen Access
  • Cite Icon51
  • https://doi.org/10.3390/rs14020355Copy DOI Icon

A Multi-Domain Collaborative Transfer Learning Method with Multi-Scale Repeated Attention Mechanism for Underwater Side-Scan Sonar Image Classification

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

Due to the strong speckle noise caused by the seabed reverberation which makes it difficult to extract discriminating and noiseless features of a target, recognition and classification of underwater targets using side-scan sonar (SSS) images is a big challenge. Moreover, unlike classification of optical images which can use a large dataset to train the classifier, classification of SSS images usually has to exploit a very small dataset for training, which may cause classifier overfitting. Compared with traditional feature extraction methods using descriptors—such as Haar, SIFT, and LBP—deep learning-based methods are more powerful in capturing discriminating features. After training on a large optical dataset, e.g., ImageNet, direct fine-tuning method brings improvement to the sonar image classification using a small-size SSS image dataset. However, due to the different statistical characteristics between optical images and sonar images, transfer learning methods—e.g., fine-tuning—lack cross-domain adaptability, and therefore cannot achieve very satisfactory results. In this paper, a multi-domain collaborative transfer learning (MDCTL) method with multi-scale repeated attention mechanism (MSRAM) is proposed for improving the accuracy of underwater sonar image classification. In the MDCTL method, low-level characteristic similarity between SSS images and synthetic aperture radar (SAR) images, and high-level representation similarity between SSS images and optical images are used together to enhance the feature extraction ability of the deep learning model. Using different characteristics of multi-domain data to efficiently capture useful features for the sonar image classification, MDCTL offers a new way for transfer learning. MSRAM is used to effectively combine multi-scale features to make the proposed model pay more attention to the shape details of the target excluding the noise. Experimental results of classification show that, in using multi-domain data sets, the proposed method is more stable with an overall accuracy of 99.21%, bringing an improvement of 4.54% compared with the fine-tuned VGG19. Results given by diverse visualization methods also demonstrate that the method is more powerful in feature representation by using the MDCTL and MSRAM.

Loading PDF

Similar Papers
  • Research Article
  • Citations7

Impact of Input Image Resolution on Deep Learning Performance for Side-Scan Sonar Classification: An Accuracy–Efficiency Analysis

  • Jul 13, 2025
  • Remote Sensing
  • Xing Du +5
  • Research Article
  • Citations15

Lambertian-based adversarial attacks on deep-learning-based underwater side-scan sonar image classification

  • Feb 08, 2023
  • Pattern Recognition
  • Qixiang Ma +2
  • PDF
  • Research Article
  • Citations53

A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images

  • Jan 18, 2023
  • Remote Sensing
  • Xing Du +4
  • PDF
  • Research Article
  • Citations24

A Texture Feature Removal Network for Sonar Image Classification and Detection

  • Jan 20, 2023
  • Remote Sensing
  • Chuanlong Li +3
  • Conference Article
  • Citations4

Seafloor Sediments Classification of Side-scan Sonar Images Based on Dual-path Network

  • Oct 17, 2022
  • Kexin Zhu +5
  • Research Article
  • Citations43

Side scan sonar image segmentation and synthesis based on extreme learning machine

  • Nov 12, 2018
  • Applied Acoustics
  • Yan Song +3
  • Conference Article
  • Citations2

Unsupervised knowledge discovery of seabed types using competitive neural network: Application to sidescan sonar images

  • Sep 01, 2014
  • Ahmed Nait Chabane +1
  • Research Article
  • Citations19

Multi-Modal Multi-Stage Underwater Side-Scan Sonar Target Recognition Based on Synthetic Images

  • Feb 26, 2023
  • Remote Sensing
  • Jian Wang +4
  • PDF
  • Research Article
  • Citations1

Side Scan Sonar Image Geocoding based on Carrier Velocity Coarseness Correction

  • Jun 01, 2020
  • Journal of Physics: Conference Series
  • Li Kai
  • Research Article
  • Citations19

Small-Sample Sonar Image Classification Based on Deep Learning

  • Nov 25, 2022
  • Journal of Marine Science and Engineering
  • Zezhou Dai +2
  • PDF
  • Research Article
  • Citations6

A Multi-Scale Fusion Strategy for Side Scan Sonar Image Correction to Improve Low Contrast and Noise Interference

  • May 15, 2024
  • Remote Sensing
  • Ping Zhou +4
  • PDF
  • Research Article
  • Citations49

Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks

  • Jul 29, 2021
  • Electronics
  • Qiang Ge +5
  • Research Article
  • Citations4

Side-Scan Sonar Image Classification Based on Joint Image Deblurring–Denoising and Pre-Trained Feature Fusion Attention Network

  • Mar 25, 2025
  • Electronics
  • Baolin Xie +2
  • Research Article
  • Citations7

Feature-based texture classification of side-scan sonar images using a neural network approach

  • Nov 05, 1992
  • Electronics Letters
  • C Shang +1
  • Research Article
  • Citations4

Target detection of man made objects in side scan sonar images - segmentation based false alarm reduction -

  • May 01, 2008
  • The Journal of the Acoustical Society of America
  • Max Neumann +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.