Detection of Underwater Multi-Targets Based on Self-Supervised Learning and Deformable Path Aggregation Feature Pyramid Network

TL;DR

This paper presents a novel underwater multi-target detection approach combining self-supervised learning with deformable and dilated convolutions, achieving improved accuracy in challenging underwater environments.

Contribution

It introduces a specialized dataset and a detection model that integrates self-supervised pre-training, deformable convolutions, and EIoU loss for enhanced underwater target detection.

Findings

Improved detection accuracy over existing methods

Effective handling of low contrast and occlusion

Enhanced feature extraction with deformable convolutions

Abstract

To overcome the constraints of the underwater environment and improve the accuracy and robustness of underwater target detection models, this paper develops a specialized dataset for underwater target detection and proposes an efficient algorithm for underwater multi-target detection. A self-supervised learning based on the SimSiam structure is employed for the pre-training of underwater target detection network. To address the problems of low detection accuracy caused by low contrast, mutual occlusion and dense distribution of underwater targets in underwater object detection, a detection model suitable for underwater target detection is proposed by introducing deformable convolution and dilated convolution. The proposed detection model can obtain more effective information by increasing the receptive field. In addition, the regression loss function EIoU is introduced, which improves model performance by separately calculating the width and height losses of the predicted box. Experiment results show that the accuracy of the underwater target detection has been improved by the proposed detector.