用于可见-红外行人重识别的模态统一网络
Modality Unifying Network for Visible-Infrared Person Re-Identification
AI总结：
针对可见-红外行人重识别中跨模态差异大、现有方法易丢失关键信息的问题，提出模态统一网络，通过生成辅助模态、设计身份与模态对齐损失提升识别性能，效果显著优于现有最优方法。
摘要：
可见-红外行人重识别（VI-ReID）因跨模态差异大、类内变化多，是一项极具挑战性的任务。现有方法主要聚焦于将不同模态嵌入同一特征空间，以学习模态共享表征。由此学到的特征虽强调了跨模态的共性模式，却抑制了对重识别极具价值的模态特异性信息与身份感知信息。为解决这些问题，我们提出一种新型模态统一网络（Modality Unifying Network, MUN），为VI-ReID探索一种鲁棒的辅助模态。首先，通过结合所提出的跨模态学习器与模态内学习器生成辅助模态，可动态建模模态特异性与模态共享表征，从而同时缓解跨模态与模态内的变化问题。其次，通过对齐三种模态的身份中心，提出一种身份对齐损失函数，以挖掘具有判别性的特征表征。第三，引入模态对齐损失，通过模态原型建模持续缩小可见图像与红外图像的分布距离。在多个公开数据集上开展的大量实验表明，所提方法以显著优势超越了当前的最优（state-of-the-art）方法。
英文摘要：
Visible-infrared person re-identification (VI-ReID) is a challenging task due to large cross-modality discrepancies and intra-class variations. Existing methods mainly focus on learning modality-shared representations by embedding different modalities into the same feature space. As a result, the learned feature emphasizes the common patterns across modalities while suppressing modality-specific and identity-aware information that is valuable for Re-ID. To address these issues, we propose a novel Modality Unifying Network (MUN) to explore a robust auxiliary modality for VI-ReID. First, the auxiliary modality is generated by combining the proposed cross-modality learner and intra-modality learner, which can dynamically model the modality-specific and modality-shared representations to alleviate both cross-modality and intra-modality variations. Second, by aligning identity centres across the three modalities, an identity alignment loss function is proposed to discover the discriminative feature representations. Third, a modality alignment loss is introduced to consistently reduce the distribution distance of visible and infrared images by modality prototype modeling. Extensive experiments on multiple public datasets demonstrate that the proposed method surpasses the current state-of-the-art methods by a significant margin.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
