• Home
  • Search
  • Self-Supervised Pre-Training Joint Framework: Assisting Lightweight Detection Network for Underwater Object Detection
  • Cite Icon22
  • https://doi.org/10.3390/jmse11030604Copy DOI Icon

Self-Supervised Pre-Training Joint Framework: Assisting Lightweight Detection Network for Underwater Object Detection

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

In the computer vision field, underwater object detection has been a challenging task. Due to the attenuation of light in a medium and the scattering of light by suspended particles in water, underwater optical images often face the problems of color distortion and target feature blurring, which greatly affect the detection accuracy of underwater object detection. Although deep learning-based algorithms have achieved state-of-the-art results in the field of object detection, most of them cannot be applied to practice because of the limited computing capacity of a low-power processor embedded in unmanned underwater vehicles. This paper proposes a lightweight underwater object detection network based on the YOLOX model called LUO-YOLOX. A novel weighted ghost-CSPDarknet and simplified PANet were used in LUO-YOLOX to reduce the parameters of the whole model. Moreover, aiming to solve the problems of color distortion and unclear features of targets in underwater images, this paper proposes an efficient self-supervised pre-training joint framework based on underwater auto-encoder transformation (UAET). After the end-to-end pre-training process with the self-supervised pre-training joint framework, the backbone of the object detection network can extract more essential and robust features from degradation images when retrained on underwater datasets. Numerous experiments on the URPC2021 and detecting underwater objects (DUO) datasets verify the performance of our proposed method. Our work can assist unmanned underwater vehicles to perform underwater object detection tasks more accurately.

Similar Papers
  • Research Article
  • Citations280

A systematic review and analysis of deep learning-based underwater object detection

  • Jan 11, 2023
  • Neurocomputing
  • Shubo Xu +5
  • Conference Article
  • Citations23

Research on the Correlation between Image Enhancement and Underwater Object Detection

  • Nov 06, 2020
  • Jiashuo Zhang +3
  • Conference Article
  • Citations11

Underwater Object Detection using Transfer Learning with Deep Learning

  • Oct 16, 2020
  • Zhu Kaiyan +2
  • Research Article
  • Citations26

Enhancing Underwater Object Detection and Classification Using Advanced Imaging Techniques: A Novel Approach with Diffusion Models

  • Aug 29, 2024
  • Sustainability
  • Prabhavathy Pachaiyappan +3
  • PDF
  • Research Article
  • Citations12

Underwater object detection algorithm based on channel attention and feature fusion

  • Apr 01, 2022
  • Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University
  • Yan Zhang +3
  • Research Article
  • Citations116

A gated cross-domain collaborative network for underwater object detection

  • Dec 27, 2023
  • Pattern Recognition
  • Linhui Dai +3
  • Research Article
  • Citations1

Underwater Image Restoration and Object Detection

  • Apr 25, 2024
  • Journal of Innovative Image Processing
  • Rohan R +4
  • Research Article
  • Citations14

A lightweight object detection framework for underwater imagery with joint image restoration and color transformation

  • Sep 14, 2023
  • Journal of King Saud University - Computer and Information Sciences
  • Ming Zhou +3
  • Research Article
  • Citations2

U-YOLOv3: A Model Focused on Underwater Object Detection

  • Jan 31, 2025
  • Informatica
  • Pratima Sarkar +2
  • PDF
  • Research Article
  • Citations219

Lightweight Underwater Object Detection Based on YOLO v4 and Multi-Scale Attentional Feature Fusion

  • Nov 21, 2021
  • Remote Sensing
  • Minghua Zhang +4
  • Research Article
  • Citations82

Real-time underwater object detection technology for complex underwater environments based on deep learning

  • Jun 08, 2024
  • Ecological Informatics
  • Hui Zhou +8
  • Research Article
  • Citations13

Underwater salient object detection jointly using improved spectral residual and Fuzzy c-Means

  • May 12, 2019
  • Journal of Intelligent & Fuzzy Systems
  • Hui Feng +5
  • Research Article
  • Citations251

Lightweight Deep Neural Network for Joint Learning of Underwater Object Detection and Color Conversion.

  • Nov 01, 2022
  • IEEE Transactions on Neural Networks and Learning Systems
  • Chia-Hung Yeh +6
  • PDF
  • Research Article
  • Citations21

Image-Fused-Guided Underwater Object Detection Model Based on Improved YOLOv7

  • Sep 27, 2023
  • Electronics
  • Zhenhua Wang +4
  • Research Article
  • Citations7

An Improved YOLOv9s Algorithm for Underwater Object Detection

  • Jan 25, 2025
  • Journal of Marine Science and Engineering
  • Shize Zhou +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.