MOS：弥合光学-SAR模态鸿沟的跨模态船舶重识别
MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification
把光学-SAR跨模态ReID的模态鸿沟拆成表征对齐与样本生成两条线：类级模态对齐损失 + 布朗桥扩散模型合成跨模态样本并在推理时做特征融合，这套「生成式跨模态补全」思路可直接迁移到可见光-红外、RGB-深度等跨模态检索与ReID任务。
原文依据 leverages a brownian bridge diffusion model to synthesize cross-modal samples, which are subsequently fused with original features during inference
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论光学与合成孔径雷达（SAR）影像之间的跨模态船舶重识别（ReID）近来已成为海上情报与监视领域中一项关键但研究不足的任务。然而，光学图像与SAR图像之间巨大的模态鸿沟给鲁棒识别带来了重大挑战。为解决该问题，我们提出MOS，一个旨在弥合光学-SAR模态鸿沟、实现模态一致特征学习以完成光学-SAR跨模态船舶重识别的新框架。MOS包含两个核心组件：（1）模态一致表征学习（MCRL）采用SAR图像去噪处理与类级模态对齐损失，以对齐跨模态的同一身份特征分布。（2）跨模态数据生成与特征融合（CDGF）利用布朗桥扩散模型合成跨模态样本，随后在推理阶段将其与原始特征融合，以增强对齐性与判别性。在HOSS ReID数据集上的大量实验表明，MOS在所有评测协议下均显著超越最优方法，在ALL to ALL、Optical to SAR与SAR to Optical三种设置下的R1准确率分别取得+3.0%、+6.2%与+16.4%的显著提升。源代码已发布于 https://github.com/yjzhao1019/MOS。
英文原文摘要 1373 字符
Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery has recently emerged as a critical yet underexplored task in maritime intelligence and surveillance. However, the substantial modality gap between optical and SAR images poses a major challenge for robust identification. To address this issue, we propose MOS, a novel framework designed to Mitigate the Optical-SAR modality gap and achieve modality-consistent feature learning for optical-SAR cross-modal ship ReID. MOS consists of two core components: (1) Modality-Consistent Representation Learning (MCRL) applies denoise SAR image procession and a class-wise modality alignment loss to align intra-identity feature distributions across modalities. (2) Cross-modal Data Generation and Feature fusion (CDGF) leverages a brownian bridge diffusion model to synthesize cross-modal samples, which are subsequently fused with original features during inference to enhance alignment and discriminability. Extensive experiments on the HOSS ReID dataset demonstrate that MOS significantly surpasses state-of-the-art methods across all evaluation protocols, achieving notable improvements of +3.0%, +6.2%, and +16.4% in R1 accuracy under the ALL to ALL,Optical to SAR, and SAR to Optical settings, respectively. The source codes are available at https://github.com/yjzhao1019/MOS.