论文标题

跨模式的当地最短路径和可见热人重新识别的全球增强

Cross-modal Local Shortest Path and Global Enhancement for Visible-Thermal Person Re-Identification

论文作者

Wang, Xiaohong, Li, Chaoqi, Ma, Xiangcai

论文摘要

除了考虑人类姿势和遮挡引起的识别难度外,还必须解决可见的 - 热跨模式重新识别(VT-REID)任务中不同成像系统引起的模态差异。在本文中,我们提出了跨模式的局部最短路径和全局增强(CM-LSP-GE)模块,这是一个基于本地和全局特征的联合学习的两流网络。我们论文的核心思想是使用局部特征对准来解决遮挡问题,并通过增强全球特征来解决模态差异。首先,基于注意力的两流重新网络网络旨在提取双模式特征并映射到统一的特征空间。然后,为了解决跨模式的人姿势和遮挡问题,将图像水平切成几个相等的部分,以获得局部特征,并且使用两个图之间的局部特征中最短路径来实现细粒度的局部特征对齐。第三,批处理归一化增强模块应用了全局特征来增强策略,从而导致不同类别之间的差异增强。多粒度损失融合策略进一步提高了算法的性能。最后,使用本地和全球特征的联合学习机制来提高跨模式的重新识别精度。两个典型数据集的实验结果表明,我们的模型显然优于最先进的方法。特别是,在SYSU-MM01数据集上,我们的模型可以在Rank-1和MAP的所有搜索术语中获得2.89%和7.96%的增益。源代码将很快发布。

In addition to considering the recognition difficulty caused by human posture and occlusion, it is also necessary to solve the modal differences caused by different imaging systems in the Visible-Thermal cross-modal person re-identification (VT-ReID) task. In this paper,we propose the Cross-modal Local Shortest Path and Global Enhancement (CM-LSP-GE) modules,a two-stream network based on joint learning of local and global features. The core idea of our paper is to use local feature alignment to solve occlusion problem, and to solve modal difference by strengthening global feature. Firstly, Attention-based two-stream ResNet network is designed to extract dual-modality features and map to a unified feature space. Then, to solve the cross-modal person pose and occlusion problems, the image are cut horizontally into several equal parts to obtain local features and the shortest path in local features between two graphs is used to achieve the fine-grained local feature alignment. Thirdly, a batch normalization enhancement module applies global features to enhance strategy, resulting in difference enhancement between different classes. The multi granularity loss fusion strategy further improves the performance of the algorithm. Finally, joint learning mechanism of local and global features is used to improve cross-modal person re-identification accuracy. The experimental results on two typical datasets show that our model is obviously superior to the most state-of-the-art methods. Especially, on SYSU-MM01 datasets, our model can achieve a gain of 2.89%and 7.96% in all search term of Rank-1 and mAP. The source code will be released soon.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源