Submarine Topography Classification Using ConDenseNet with Label Smoothing Regularization
Open Access
- 3 August 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (15) , 2686
Abstract
The classification of submarine topography and geomorphology is essential for marine resource exploitation and ocean engineering, with wide-ranging implications in marine geology, disaster assessment, resource exploration, and autonomous underwater navigation. Submarine landscapes are highly complex and diverse. Traditional visual interpretation methods are not only inefficient and subjective but also lack the precision required for high-accuracy classification. While many machine learning and deep learning models have achieved promising results in image classification, limited work has been performed on integrating backscatter and bathymetric data for multi-source processing. Existing approaches often suffer from high computational costs and excessive hyperparameter demands. In this study, we propose a novel approach that integrates pruning-enhanced ConDenseNet with label smoothing regularization to reduce misclassification, strengthen the cross-entropy loss function, and significantly lower model complexity. Our method improves classification accuracy by 2% to 10%, reduces the number of hyperparameters by 50% to 96%, and cuts computation time by 50% to 85.5% compared to state-of-the-art models, including AlexNet, VGG, ResNet, and Vision Transformer. These results demonstrate the effectiveness and efficiency of our model for multi-source submarine topography classification.Keywords
Funding Information
- Deep Earth Probe and Mineral Resources Exploration—National Science and Technology Major Project
This publication has 68 references indexed in Scilit:
- A review of convolutional neural networks in computer visionArtificial Intelligence Review, 2024
- Seafloor geomorphology of the northern Argentine continental slope at 40-41° S mapped from high-resolution bathymetryJournal of South American Earth Sciences, 2023
- An imaging algorithm for high-resolution imaging sonar systemMultimedia Tools and Applications, 2023
- Seismic Data Denoising Using a Self-Supervised Deep Learning NetworkMathematical Geosciences, 2023
- CNN Multibeam Seabed Sediment Classification Combined with a Novel Feature Optimization MethodMathematical Geosciences, 2023
- Diving deep: the centuries-long quest to explore the deepest oceanNature, 2023
- Rethinking general underwater object detection: Datasets, challenges, and solutionsNeurocomputing, 2022
- Review on deep learning techniques for marine object recognition: Architectures and algorithmsControl Engineering Practice, 2022
- Deep learning model for seabed sediment classification based on fuzzy ranking feature optimizationMarine Geology, 2021
- Seabed sediment classification using multibeam backscatter data based on the selecting optimal random forest modelApplied Acoustics, 2020