Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship Classification

Ship image classification identifies the type of ships in an input image, which plays a significant role in the marine field. To enhance the ship classification performance, various research focuses on studying multi-modal ship classification, which aims at combining the advantages of visible images...

Full description

Saved in:
Bibliographic Details
Main Authors: Xin Song, Zhikui Chen, Fangming Zhong, Jing Gao, Jianning Zhang, Peng Li
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/22/7298
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152459885477888
author Xin Song
Zhikui Chen
Fangming Zhong
Jing Gao
Jianning Zhang
Peng Li
author_facet Xin Song
Zhikui Chen
Fangming Zhong
Jing Gao
Jianning Zhang
Peng Li
author_sort Xin Song
collection DOAJ
description Ship image classification identifies the type of ships in an input image, which plays a significant role in the marine field. To enhance the ship classification performance, various research focuses on studying multi-modal ship classification, which aims at combining the advantages of visible images and infrared images to capture complementary information. However, the current methods simply concatenate features of different modalities to learn complementary information, which neglects the multi-level correlation between different modalities. Moreover, the existing methods require a large amount of labeled ship images to train the model. How to capture the multi-level cross-modal correlation between unlabeled and labeled data is still a challenge. In this paper, a novel semi-supervised multi-modal ship classification approach is proposed to solve these issues, which consists of two components, i.e., multi-level cross-modal interactive network and semi-supervised contrastive learning strategy. To learn comprehensive complementary information for classification, the multi-level cross-modal interactive network is designed to build local-level and global-level cross-modal feature correlation. Then, the semi-supervised contrastive learning strategy is employed to drive the optimization of the network with the intra-class consistency constraint based on supervision signals of unlabeled samples and prior label information. Extensive experiments on the public datasets demonstrate that our approach achieves state-of-the-art semi-supervised classification effectiveness.
format Article
id doaj-art-e806afdb2b8d4a91aa8bf4c6d33bb203
institution Kabale University
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e806afdb2b8d4a91aa8bf4c6d33bb2032024-11-26T18:21:26ZengMDPI AGSensors1424-82202024-11-012422729810.3390/s24227298Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship ClassificationXin Song0Zhikui Chen1Fangming Zhong2Jing Gao3Jianning Zhang4Peng Li5The School of Software Technology, Dalian University of Technology, Dalian 116621, ChinaThe School of Software Technology, Dalian University of Technology, Dalian 116621, ChinaThe School of Software Technology, Dalian University of Technology, Dalian 116621, ChinaThe School of Software Technology, Dalian University of Technology, Dalian 116621, ChinaThe School of Software Technology, Dalian University of Technology, Dalian 116621, ChinaThe School of Software Technology, Dalian University of Technology, Dalian 116621, ChinaShip image classification identifies the type of ships in an input image, which plays a significant role in the marine field. To enhance the ship classification performance, various research focuses on studying multi-modal ship classification, which aims at combining the advantages of visible images and infrared images to capture complementary information. However, the current methods simply concatenate features of different modalities to learn complementary information, which neglects the multi-level correlation between different modalities. Moreover, the existing methods require a large amount of labeled ship images to train the model. How to capture the multi-level cross-modal correlation between unlabeled and labeled data is still a challenge. In this paper, a novel semi-supervised multi-modal ship classification approach is proposed to solve these issues, which consists of two components, i.e., multi-level cross-modal interactive network and semi-supervised contrastive learning strategy. To learn comprehensive complementary information for classification, the multi-level cross-modal interactive network is designed to build local-level and global-level cross-modal feature correlation. Then, the semi-supervised contrastive learning strategy is employed to drive the optimization of the network with the intra-class consistency constraint based on supervision signals of unlabeled samples and prior label information. Extensive experiments on the public datasets demonstrate that our approach achieves state-of-the-art semi-supervised classification effectiveness.https://www.mdpi.com/1424-8220/24/22/7298ship classificationdeep multi-modal learningsemi-supervised learning
spellingShingle Xin Song
Zhikui Chen
Fangming Zhong
Jing Gao
Jianning Zhang
Peng Li
Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship Classification
Sensors
ship classification
deep multi-modal learning
semi-supervised learning
title Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship Classification
title_full Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship Classification
title_fullStr Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship Classification
title_full_unstemmed Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship Classification
title_short Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship Classification
title_sort multi level cross modal interactive network based semi supervised multi modal ship classification
topic ship classification
deep multi-modal learning
semi-supervised learning
url https://www.mdpi.com/1424-8220/24/22/7298
work_keys_str_mv AT xinsong multilevelcrossmodalinteractivenetworkbasedsemisupervisedmultimodalshipclassification
AT zhikuichen multilevelcrossmodalinteractivenetworkbasedsemisupervisedmultimodalshipclassification
AT fangmingzhong multilevelcrossmodalinteractivenetworkbasedsemisupervisedmultimodalshipclassification
AT jinggao multilevelcrossmodalinteractivenetworkbasedsemisupervisedmultimodalshipclassification
AT jianningzhang multilevelcrossmodalinteractivenetworkbasedsemisupervisedmultimodalshipclassification
AT pengli multilevelcrossmodalinteractivenetworkbasedsemisupervisedmultimodalshipclassification