Person re-identification based on multi-scale feature learning
Person re-identification based on multi-scale feature learning
复制标题
基于多尺度特征学习的行人重识别
DOI：
10.1016/j.knosys.2021.107281
复制
发表时间：
2021-07-08
影响因子：
8.8
通讯作者：
Zhang, Huaxiang
中科院分区：
文献类型：
--
作者：
Li, Yueying;Liu, Li;Zhang, Huaxiang
行人特征提取是人脸再识别的有效方法。大多数人的再识别工作侧重于从网络的高层提取抽象特征，而忽略了中间层特征，从而降低了身份的准确性。为了解决这一问题，我们构建了一个平滑聚合模块（SAM）来提取、对齐和融合网络中间层的特征映射，以弥补高层次网络特征中细节信息的不足，并提出了一种全尺度特征聚合方法（OSFA）(1)来共同学习抽象特征和局部细节特征。考虑到人再识别中的类内距离要小于类间距离，我们结合多重损失对模型进行约束。我们在三个标准基准数据集上评估了我们的方法的性能：Market-1501， CUHK03（检测和标记）和DukeMTMC-reID，实验结果表明我们的方法优于最先进的方法。(C) 2021 Elsevier B.V.版权所有
Extracting discriminative pedestrian features is an effective method in person re-identification. Most person re-identification works focus on extracting abstract features from the high-layer of the network, but ignore the middle-layer features, thus reducing the identity accuracy. To solve this problem, we construct a Smooth Aggregation Module (SAM) to extract, align, and fuse the feature maps in the middle-layer of the network to make up for the lack of detailed information in the high-level network features, and propose an Omni-Scale Feature Aggregation method (OSFA)(1) to jointly learn the abstract features and local detail features. Considering that the intra-class distance in person re-identification should be less than the inter-class distance, we combine multiple losses to constrain the model. We evaluate the performance of our method on three standard benchmark datasets: Market-1501, CUHK03 (both detected and labeled) and DukeMTMC-reID, and experimental results show that our method is superior to the state-of-the-art approaches. (C) 2021 Elsevier B.V. All rights reserved.