A Multi-Domain Collaborative Transfer Learning Method with Multi-Scale Repeated Attention Mechanism for Underwater Side-Scan Sonar Image Classification
TL;DR: 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 and is shown to be more powerful in feature representation by using the MDCTL and MSRAM.
read more
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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Survey on deep learning based computer vision for sonar imagery
TL;DR: A broad overview of deep learning methods for feature extraction, classification, detection and segmentation of sidecan and synthetic aperture sonar images can be found in this article , where the authors propose to leverage the research in this field by combining available data into an open source dataset as well as carrying out comparative studies on developed deep learning algorithms.
61
ShipGeoNet: SAR Image-Based Geometric Feature Extraction of Ships Using Convolutional Neural Networks
Muhammad Yasir,Shanwei Liu,Mingming Xu,Jianhua Wan,Saied Pirasteh,Kinh Bac Dang +5 more
TL;DR: The ShipGeoNet model, a model designed to extract geometric features from ships captured in Sentinel-1 synthetic aperture radar (SAR) images, is introduced, opening up possibilities for future applications in maritime surveillance, navigation, and environmental monitoring.
26
Small Target Detection Method Based on Low-Rank Sparse Matrix Factorization for Side-Scan Sonar Images
TL;DR: In this paper , a low-rank sparse matrix factorization method was proposed for target detection in side-scan sonar images, which is based on the robust principal component analysis (RPCA).
Deep Learning Algorithms for Sonar Imagery Analysis and its Application in Aquaculture: A Review
Yingqian Chai,Huihui Yu,Ling Xu,Daoliang Li +3 more
TL;DR: Research of DL-based algorithms for sonar imagery, including denoising, feature extraction, classification, detection, and segmentation, are outlined, showing that sonar image classification is the most studied and transfer learning has put into spotlight.
8
Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data Analysis
TL;DR: In this paper , the authors proposed a solution based on convolutional neural networks with bilinear pooling in order to achieve higher values of classification accuracy for side-scan sonar (SSS) images.
8
References
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick,Jeff Donahue,Trevor Darrell,Jitendra Malik +3 more
- 23 Jun 2014
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
A Survey on Transfer Learning
Sinno Jialin Pan,Qiang Yang +1 more
TL;DR: The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.
•Posted Content
Squeeze-and-Excitation Networks
TL;DR: Squeeze-and-excitation (SE) as mentioned in this paper adaptively recalibrates channel-wise feature responses by explicitly modeling interdependencies between channels, which can be stacked together to form SENet architectures.
18.9K
CBAM: Convolutional Block Attention Module
Sanghyun Woo,Jongchan Park,Joon-Young Lee,In So Kweon +3 more
- 08 Sep 2018
TL;DR: Convolutional Block Attention Module (CBAM) as discussed by the authors is a simple yet effective attention module for feed-forward convolutional neural networks, given an intermediate feature map, the module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement.