Multi-Feature Collaborative Fusion Network with Deep Supervision for SAR Ship Classification

Zheng, Hao and Hu, Zhigang and Yang, Liu and Xu, Aikun and Zheng, Meiguang and Zhang, Ce and Li, Keqin (2023) Multi-Feature Collaborative Fusion Network with Deep Supervision for SAR Ship Classification. IEEE Transactions on Geoscience and Remote Sensing, 61: 5212614. pp. 1-14. ISSN 0196-2892

[thumbnail of Multi-Feature Collaborative Fusion Network with Deep Supervision for SAR Ship Classification]
Text (Multi-Feature Collaborative Fusion Network with Deep Supervision for SAR Ship Classification)
Multi_Feature_Collaborative_Fusion_Network_with_Deep_Supervision_for_SAR_Ship_Classification.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (7MB)


Multifeature synthetic aperture radar (SAR) ship classification aims to build models that can process, correlate, and fuse information from both handcrafted and deep features. Although handcrafted features provide rich expert knowledge, current fusion methods inadequately explore the relatively significant role of handcrafted features in conjunction with deep features, the imbalances in feature contributions, and the cooperative ways in which features learn. In this article, we propose a novel multifeature collaborative fusion network with deep supervision (MFCFNet) to effectively fuse handcrafted features and deep features for SAR ship classification tasks. Specifically, our framework mainly includes two types of feature extraction branches, a knowledge supervision and collaboration module (KSCM) and a feature fusion and contribution assignment module (FFCA). The former module improves the quality of the feature maps learned by each branch through auxiliary feature supervision and introduces a synergy loss to facilitate the interaction of information between deep features and handcrafted features. The latter module utilizes an attention mechanism to adaptively balance the importance among various features and assign the corresponding feature contributions to the total loss function based on the generated feature weights. We conducted extensive experimental and ablation studies on two public datasets, OpenSARShip-1.0 and FUSAR-Ship, and the results show that MFCFNet is effective and outperforms single deep feature and multifeature models based on previous internal FC layer and terminal FC layer fusion. Furthermore, our proposed MFCFNet exhibits better performance than the current state-of-the-art methods.

Item Type:
Journal Article
Journal or Publication Title:
IEEE Transactions on Geoscience and Remote Sensing
Uncontrolled Keywords:
Research Output Funding/yes_externally_funded
?? multi-feature fusionhandcrafted featuredeep supervisionsynthetic aperture radar (sar)sar ship classificationyes - externally fundednoelectrical and electronic engineeringgeneral earth and planetary sciencesearth and planetary sciences(all) ??
ID Code:
Deposited By:
Deposited On:
24 Jul 2023 08:50
Last Modified:
16 Jul 2024 12:05