SDF-Net: Structure-Aware Disentangled Feature Learning for Opticall-SAR Ship Re-identification

TL;DR

SDF-Net introduces a structure-aware, disentangled feature learning approach for cross-modal ship re-identification, leveraging geometric consistency to improve robustness against radiometric discrepancies between optical and SAR images.

Contribution

The paper proposes a novel ViT-based network that incorporates geometric structure constraints and disentangles identity and modality features for optical-SAR ship ReID.

Findings

Outperforms existing methods on HOSS-ReID dataset

Effectively disentangles modality-invariant and specific features

Utilizes structure consistency to enhance robustness against radiometric variations

Abstract

Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery is fundamentally challenged by the severe radiometric discrepancy between passive optical imaging and coherent active radar sensing. While existing approaches primarily rely on statistical distribution alignment or semantic matching, they often overlook a critical physical prior: ships are rigid objects whose geometric structures remain stable across sensing modalities, whereas texture appearance is highly modality-dependent. In this work, we propose SDF-Net, a Structure-Aware Disentangled Feature Learning Network that systematically incorporates geometric consistency into optical--SAR ship ReID. Built upon a ViT backbone, SDF-Net introduces a structure consistency constraint that extracts scale-invariant gradient energy statistics from intermediate layers to robustly anchor representations against radiometric variations. At the terminal stage, SDF-Net disentangles the learned representations into modality-invariant identity features and modality-specific characteristics. These decoupled cues are then integrated through a parameter-free additive residual fusion, effectively enhancing discriminative power. Extensive experiments on the HOSS-ReID dataset demonstrate that SDF-Net consistently outperforms existing state-of-the-art methods. The code and trained models are publicly available at https://github.com/cfrfree/SDF-Net.