用于空地摄像头网络下行人重识别的视角解耦Transformer
View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network
AI总结：
针对空地行人重识别中视角差异大的挑战，提出视角解耦Transformer框架，通过层级减法分离和正交损失解耦特征，并构建大规模数据集CARGO，实验证明该方法有效提升了识别性能。
摘要：
现有行人重识别方法在同构摄像头（如地面-地面匹配）的基于外观的身份关联上取得了显著进展。然而，作为更实际的场景，异构摄像头间的空地行人重识别（AGPReID）却极少受到关注。为缓解视角巨大差异对判别性身份表示的破坏这一AGPReID中最重大的挑战，本文提出了视角解耦Transformer（VDT）这一简单有效的框架。VDT设计了两个主要组件来解耦视角相关与视角无关特征，即层级减法分离和正交损失，前者在VDT内部分离这两种特征，后者约束两者保持独立。此外，我们贡献了一个名为CARGO的大规模AGPReID数据集，包含5个航拍/8个地面摄像头、5,000个身份和108,563张图像。在两个数据集上的实验表明，VDT是可行且有效的AGPReID解决方案，在CARGO和AG-ReID上的mAP/Rank1分别超越先前方法高达5.0%/2.7%和3.7%/5.2%，且保持同等量级的计算复杂度。项目地址：https://github.com/LinlyAC/VDT-AGPReID
英文摘要：
Existing person re-identification methods have achieved remarkable advances in appearance-based identity association across homogeneous cameras, such as ground-ground matching. However, as a more practical scenario, aerial-ground person re-identification (AGPReID) among heterogeneous cameras has received minimal attention. To alleviate the disruption of discriminative identity representation by dramatic view discrepancy as the most significant challenge in AGPReID, the view-decoupled transformer (VDT) is proposed as a simple yet effective framework. Two major components are designed in VDT to decouple view-related and view-unrelated features, namely hierarchical subtractive separation and orthogonal loss, where the former separates these two features inside the VDT, and the latter constrains these two to be independent. In addition, we contribute a large-scale AGPReID dataset called CARGO, consisting of five/eight aerial/ground cameras, 5,000 identities, and 108,563 images. Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5.0%/2.7% on CARGO and 3.7%/5.2% on AG-ReID, keeping the same magnitude of computational complexity. Our project is available at https://github.com/LinlyAC/VDT-AGPReID
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。
