弥合差距：用于可见光-红外行人重识别的多级跨模态联合对齐
Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-Identification
AI总结：
提出多级跨模态联合对齐（MCJA）方法，通过模态对齐增强和跨模态检索损失，有效弥合可见光-红外行人重识别中的模态与优化目标差距，仅基于全局特征即表现优异。
摘要：
可见光-红外行人重识别（VI-ReID）是一项具有挑战性的跨模态图像检索任务，旨在跨可见光和红外摄像头匹配行人的图像。为了解决模态差距，现有的主流方法采用一种学习范式，将图像检索任务转换为带有交叉熵损失和辅助度量学习损失的图像分类任务。这些损失遵循调整提取的嵌入分布的策略，以减少类内距离并增加类间距离。然而，这样的目标并不能精确对应检索任务的最终测试设置，从而在优化层面上导致了新的差距。通过重新思考VI-ReID的这些关键点，我们提出了一种简单有效的方法，即多级跨模态联合对齐（MCJA），弥合了模态和目标层面的差距。对于前者，我们设计了模态对齐增强，由三种新颖的策略组成：加权灰度、跨通道cutmix和频谱抖动增强，有效地减少了图像空间中的模态差异。对于后者，我们引入了一种新的跨模态检索损失。这是首个从排序列表的角度进行约束的工作，与测试阶段的目标保持一致。此外，仅基于全局特征，我们的方法展现出良好的性能，可以作为VI-ReID社区的强基线方法。
英文摘要：
Visible-Infrared person Re-IDentification (VI-ReID) is a challenging cross-modality image retrieval task that aims to match pedestrians' images across visible and infrared cameras. To solve the modality gap, existing mainstream methods adopt a learning paradigm converting the image retrieval task into an image classification task with cross-entropy loss and auxiliary metric learning losses. These losses follow the strategy of adjusting the distribution of extracted embeddings to reduce the intra-class distance and increase the inter-class distance. However, such objectives do not precisely correspond to the final test setting of the retrieval task, resulting in a new gap at the optimization level. By rethinking these keys of VI-ReID, we propose a simple and effective method, the Multi-level Cross-modality Joint Alignment (MCJA), bridging both modality and objective-level gap. For the former, we design the Modality Alignment Augmentation, which consists of three novel strategies, the weighted grayscale, cross-channel cutmix, and spectrum jitter augmentation, effectively reducing modality discrepancy in the image space. For the latter, we introduce a new Cross-Modality Retrieval loss. It is the first work to constrain from the perspective of the ranking list, aligning with the goal of the testing stage. Moreover, based on the global feature only, our method exhibits good performance and can serve as a strong baseline method for the VI-ReID community.
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。
