双向多步域泛化用于可见光-红外行人重识别
Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification
AI总结：
针对可见光-红外行人重识别的跨模态差异问题，提出双向多步域泛化（BMDG）方法，通过学习对齐身体部位特征创建虚拟中间域，分两步最小化跨模态差距，实验表明其性能优于现有方法且可增强其他基于部位的方法。
摘要：
可见光-红外行人重识别（V-I ReID）的一个关键挑战是训练能够有效解决跨模态显著差异的骨干模型。生成单一中间桥接域的最先进方法通常效果较差，因为该生成域可能无法充分捕捉足够的共同判别信息。本文介绍双向多步域泛化（BMDG），这是一种用于统一不同模态特征表示的新方法。BMDG通过学习和对齐从I和V模态提取的身体部位特征，创建多个虚拟中间域。具体而言，我们的方法旨在通过两个步骤最小化跨模态差距。首先，BMDG通过从V和I图像中学习共享且模态不变的身体部位原型，在特征空间中对齐模态。然后，它通过应用双向多步学习来泛化特征表示，该学习在每一步中逐步细化特征表示，并整合来自两种模态的更多原型。基于这些原型，多个桥接步骤增强了特征表示。在V-I ReID数据集上进行的实验表明，我们的BMDG方法可以优于最先进的基于部位和中间生成方法，并且可以集成到其他基于部位的方法中以提高其V-I ReID性能。（我们的代码可在：https:/alehdaghi.github.io/BMDG/ 获取）
英文摘要：
A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single intermediate bridging domain are often less effective, as this generated domain may not adequately capture sufficient common discriminant information. This paper introduces Bidirectional Multi-step Domain Generalization (BMDG), a novel approach for unifying feature representations across diverse modalities. BMDG creates multiple virtual intermediate domains by learning and aligning body part features extracted from both I and V modalities. In particular, our method aims to minimize the cross-modal gap in two steps. First, BMDG aligns modalities in the feature space by learning shared and modality-invariant body part prototypes from V and I images. Then, it generalizes the feature representation by applying bidirectional multi-step learning, which progressively refines feature representations in each step and incorporates more prototypes from both modalities. Based on these prototypes, multiple bridging steps enhance the feature representation. Experiments conducted on V-I ReID datasets indicate that our BMDG approach can outperform state-of-the-art part-based and intermediate generation methods, and can be integrated into other part-based methods to enhance their V-I ReID performance. (Our code is available at:https:/alehdaghi.github.io/BMDG/ )
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。
