Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning
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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/134 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548971810488320 |
|---|---|
| author | Ye Peng Houpu Li Wenwen Zhang Junhui Zhu Lei Liu Guojun Zhai |
| author_facet | Ye Peng Houpu Li Wenwen Zhang Junhui Zhu Lei Liu Guojun Zhai |
| author_sort | Ye Peng |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-1bbcac5f1834482da75b6513933cade8 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-1bbcac5f1834482da75b6513933cade82025-01-10T13:20:20ZengMDPI AGRemote Sensing2072-42922025-01-0117113410.3390/rs17010134Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot LearningYe Peng0Houpu Li1Wenwen Zhang2Junhui Zhu3Lei Liu4Guojun Zhai5School of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Power Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaKey Laboratory of Geological Exploration and Evaluation, Ministry of Education, China University of Geosciences, Wuhan 430074, ChinaSonar 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.https://www.mdpi.com/2072-4292/17/1/134underwater sonar image classificationpseudo-sonar image generationzero-shot learning |
| spellingShingle | Ye Peng Houpu Li Wenwen Zhang Junhui Zhu Lei Liu Guojun Zhai Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning Remote Sensing underwater sonar image classification pseudo-sonar image generation zero-shot learning |
| title | Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning |
| title_full | Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning |
| title_fullStr | Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning |
| title_full_unstemmed | Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning |
| title_short | Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning |
| title_sort | underwater sonar image classification with image disentanglement reconstruction and zero shot learning |
| topic | underwater sonar image classification pseudo-sonar image generation zero-shot learning |
| url | https://www.mdpi.com/2072-4292/17/1/134 |
| work_keys_str_mv | AT yepeng underwatersonarimageclassificationwithimagedisentanglementreconstructionandzeroshotlearning AT houpuli underwatersonarimageclassificationwithimagedisentanglementreconstructionandzeroshotlearning AT wenwenzhang underwatersonarimageclassificationwithimagedisentanglementreconstructionandzeroshotlearning AT junhuizhu underwatersonarimageclassificationwithimagedisentanglementreconstructionandzeroshotlearning AT leiliu underwatersonarimageclassificationwithimagedisentanglementreconstructionandzeroshotlearning AT guojunzhai underwatersonarimageclassificationwithimagedisentanglementreconstructionandzeroshotlearning |