9 January 2024 in ISPRS Journal of Photogrammetry and Remote Sensing
14 March 2025 in IEEE Transactions on Instrumentation and Measurement
In synthetic aperture radar (SAR) target recognition, combining the physical model of electromagnetic scattering with SAR images can effectively enhance the generalization of recognition models. However, the significant representation discrepancy obstructs the full utilization of electromagnetic characteristics. This weakens the effectiveness and robustness of recognition systems. In order to solve this problem, we propose a bidirectional interaction fusion network based on electromagnetic characteristic-maps (EC-Maps) and SAR images, referred to BFEI. Specifically, EC-Maps are constructed based on the attributed scattering center (ASC) physical model using polar format imaging algorithm. They reflect electromagnetic characteristics of targets in image format instead of the parameter matrices of ASCs. The consistent formats of EC-Maps and SAR images facilitate the utilization of electromagnetic characteristics and the interaction between different modalities. Subsequently, the bidirectional interactions between EC-Maps and SAR images are achieved using cross-attention operations. With the interactions, transferable and homogeneous features between the two modalities can be extracted, thereby enabling them to corroborate each other. Finally, a decision fusion module is used to further leverage the complementary knowledge between the two modalities for classification. Extensive experiments conducted on the Moving and Stationary Target Acquisition and Recognition dataset and FUSAR-ship dataset demonstrate the superiority and robustness of BFEI under different observation conditions. Particularly, BFEI outperforms other state-of-the-art methods in recognition accuracy on the FUSAR-ship dataset.
16 May 2025 in Pattern Recognition
25 December 2025 in IEEE Transactions on Aerospace and Electronic Systems
Synthetic Aperture Radar (SAR) offers day-and-night capability for ship recognition, but its scattering mechanism results in limited textural and spectral detail compared to optical imagery, hindering fine-grained semantic interpretation and recognition. Existing cross-modal transfer methods mainly align features or pixels between SAR and optical imagery, yet they fail to guarantee semantic consistency across modalities. To address this, we propose a Semantic-anchored Cross-modal Distillation Framework (SCDF) with foundation models. SCDF introduces textual semantic descriptors for each ship category as semantic anchors to ensure cross-modal semantic consistency, while incorporating scattering topology maps into SAR images, thus enabling effective transfer without sacrificing modality-specific discriminability. Within this framework, a language foundation model encodes semantic anchors into text embeddings as class references, formulating ship recognition as aligning visual features with semantic anchors. To enhance the alignment between SAR features and anchors, a scattering-aware student model integrates scattering topology maps with SAR imagery, emphasizing key ship structures. This alignment is further guided by a vision foundation model acting as the optical teacher, which provides reliable optical-semantic similarity for distillation. Instead of simply transferring labels or features, the semantic-anchored distillation transfers semantic discriminability from the optical domain to SAR while preserving SAR-specific scattering topology features. Extensive experiments on the FUSAR-Ship dataset and fine-grained optical datasets (FGSC-23 and FGSCR-42) demonstrate that SCDF effectively bridges SAR and optical imagery and enhances SAR ship recognition.