Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning
Remote Sensing · 02.01.2025 · 17 (1) · 134
DOI: 10.3390/rs17010134 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.01.2025. Verfasst von Ye Peng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation for Outstanding Young Scholars, National Natural Science Foundation of China.
Abstract (Originalsprache)
Sonar is a valuable tool for ocean exploration since it can obtain a wealth of data. With the development of intelligent technology, deep learning has brought new vitality to underwater sonar image classification. However, due to the difficulty and high cost of acquiring underwater sonar images, we have to consider the extreme case when there are no available sonar data of a specific category, and how to improve the prediction ability of intelligent classification models for unseen sonar data. In this work, we design an underwater sonar image classification method based on Image Disentanglement Reconstruction and Zero-Shot Learning (IDR-ZSL). Initially, an image disentanglement reconstruction (IDR) network is proposed for generating pseudo-sonar samples. The IDR consists of two encoders, a decoder, and three discriminators. The first encoder is responsible for extracting the structure vectors of the optical images and the texture vectors of the sonar images; the decoder is in charge of combining the above vectors to generate the pseudo-sonar images; and the second encoder is in charge of disentangling the pseudo-sonar images. Furthermore, three discriminators are incorporated to determine the realness and texture quality of the reconstructed image and feedback to the decoder. Subsequently, the underwater sonar image classification model performs zero-shot learning based on the generated pseudo-sonar images. Experimental results show that IDR-ZSL can generate high-quality pseudo-sonar images, and improve the prediction accuracy of the zero-shot classifier on unseen classes of sonar images.
Förderung
- National Science Foundation for Outstanding Young Scholars
- National Natural Science Foundation of China
Zitieren
APA
Peng, Y., Li, H., Zhang, W., Zhu, J., Liu, L., & Zhai, G. (2025). Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning. Remote Sensing, 17(1), 134. https://doi.org/10.3390/rs17010134
Vancouver
Peng Y, Li H, Zhang W, Zhu J, Liu L, Zhai G. Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning. Remote Sensing. 2025;17(1):134. doi:10.3390/rs17010134
BibTeX
@article{Peng2025,
author = {Peng, Ye and Li, Houpu and Zhang, Wenwen and Zhu, Junhui and Liu, Lei and Zhai, Guojun},
title = {Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {1},
pages = {134},
doi = {10.3390/rs17010134}
}
EUVIMED