Attribute-Guided Collaborative Learning for Partial Person Re-Identification
Attribute-Guided Collaborative Learning for Partial Person Re-Identification
复制标题
DOI：
10.1109/tpami.2023.3312302
复制
发表时间：
2023-09
影响因子：
23.6
通讯作者：
Haoyu Zhang;Meng Liu;Yuhong Li;Ming Yan;Zan Gao;Xiaojun Chang;Liqiang Nie
中科院分区：
文献类型：
--
作者：
Haoyu Zhang;Meng Liu;Yuhong Li;Ming Yan;Zan Gao;Xiaojun Chang;Liqiang Nie
部分行人重识别（ReID）旨在解决由于遮挡或视野外导致的图像空间错位问题。尽管通过引入附加信息（例如人体姿势地标、掩模图和空间信息）取得了重大进展，但由于噪声关键点和易受影响的行人表示，部分人物 ReID 仍然具有挑战性。为了解决这些问题，我们提出了一种统一的属性引导的部分行人 ReID 协作学习方案。具体来说，我们引入了一种自适应阈值引导掩模图卷积网络，它可以动态删除不可信的边缘以抑制噪声关键点的扩散。此外，我们结合了人类属性并设计了一种循环异构图卷积网络，通过图内和图间交互有效地融合跨模式行人信息，从而产生稳健的行人表示。最后，为了增强关键点表示学习，我们根据人体的轴对称特性设计了一种新颖的基于部位的相似性约束。对多个公共数据集的广泛实验表明，与其他最先进的基线相比，我们的模型实现了卓越的性能。
Partial person re-identification (ReID) aims to solve the problem of image spatial misalignment due to occlusions or out-of-views. Despite significant progress through the introduction of additional information, such as human pose landmarks, mask maps, and spatial information, partial person ReID remains challenging due to noisy keypoints and impressionable pedestrian representations. To address these issues, we propose a unified attribute-guided collaborative learning scheme for partial person ReID. Specifically, we introduce an adaptive threshold-guided masked graph convolutional network that can dynamically remove untrustworthy edges to suppress the diffusion of noisy keypoints. Furthermore, we incorporate human attributes and devise a cyclic heterogeneous graph convolutional network to effectively fuse cross-modal pedestrian information through intra- and inter-graph interaction, resulting in robust pedestrian representations. Finally, to enhance keypoint representation learning, we design a novel part-based similarity constraint based on the axisymmetric characteristic of the human body. Extensive experiments on multiple public datasets have shown that our model achieves superior performance compared to other state-of-the-art baselines.