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

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.

Sonar image intelligent processing in seabed pipeline detection: review and application

“…Furthermore, in order to obtain a more accurate sonar image dataset of seabed targets, Cheng et al proposed a multi-domain cooperative transfer learning method with a multi-scale repeated attention mechanism based on the SIFT algorithm. It improves the accuracy of underwater sonar image classification [91].…”

An Underwater Side-Scan Sonar Transfer Recognition Method Based on Crossed Point-to-Point Second-Order Self-Attention Mechanism

“…Moreover, disparities between composite and SSS image samples directly influence the target recognition outcome. Cheng et al [40] enhanced the noise resistance and recognition precision of the VGG-19 network by training its middle layer with synthetic aperture radar (SAR) data. Wang et al [41] employed ResNet-152 as the foundational network for target transfer recognition and introduced the location attention mechanism considering channel factors and the channel attention mechanism considering location factors.…”

D2MFNet: a Dual-Domain Multi-Frequency Network for Side-Scan Sonar Image Detection

“…Li et al [48] had proposed a transfer learning method for sonar image classification and target detection called the texture feature removal network, to deal with the problem of few targets in sonar images. Cheng et al [49] had proposed a multi-domain collaborative transfer learning (MDCTL) method with multi-scale repeated attention mechanism (MSRAM) for improving the accuracy of underwater sonar image classification.…”