PrGCN: Probability prediction with graph convolutional network for person re-identification
PrGCN: Probability prediction with graph convolutional network for person re-identification
复制标题
PrGCN：利用图卷积网络进行人员重新识别的概率预测
DOI：
10.1016/j.neucom.2020.10.019
复制
发表时间：
2021-01-29
期刊：
影响因子：
6
通讯作者：
Jiang, Guoquan
中科院分区：
文献类型：
--
作者：
Liu, Hongmin;Xiao, Zhenzhen;Jiang, Guoquan
鲁棒的相似性度量是人物再识别的一个重要问题。大多数现有的ReID模型通过计算它们的欧氏距离来估计查询图像和图库图像之间的相似性，而忽略了图像空间中包含的丰富上下文信息。本文提出了一种基于图卷积网络（GCN）的方法来改进ReID中的相似性度量，该方法将ReID任务视为节点对之间链接概率的预测问题。我们的方法被命名为PrGCN（概率GCN），其中每个人被视为一个实例节点。首先，为每个实例节点构造一个以实例为中心的子图（ICS）来描述其丰富的局部上下文信息。其次，构造的ICS输入到GCN推断和预测节点对的链接概率，然后根据预测的概率进行查询和图库图像之间的相似性排名。大量的实验表明，该方法显着提高了ReID的mAP和Top-1准确度，在各种基准测试（Market 1501，DukeMTMC-ReID和CUHK 03）上获得了比最先进的方法更好或相当的结果。此外，我们验证了所提出的PrGCN可以很容易地嵌入到其他深度学习架构中，以取代欧几里得距离度量，并实现显着的性能改进。(c)2020 Elsevier B. V.保留所有权利。
Robust similarity measurement is an important issue for person re-identification (ReID). Most existing ReID models estimate the similarity between query and gallery images by computing their Euclidean distances while ignoring the rich context information contained in the image space. In this paper, we pro pose a graph convolutional network (GCN) based method to improve the similarity measurement in ReID, which regards the ReID task as a prediction problem of the link probability between node pairs. Our method is named as PrGCN (Probability GCN), in which each person is regarded as an instance node. Firstly, an Instance Centered Sub-graphs (ICS) is constructed for each instance node to depict its rich local context information. Secondly, the constructed ICS is input to a GCN to infer and predict the link probability of node pairs, followed by a similarity ranking between the query and gallery images according to the predicted probabilities. Extensive experiments show that the proposed method improves the mAP and Top-1 accuracy of ReID significantly, yielding better or comparable results to the state-of-the-art methods on various benchmarks (Market1501, DukeMTMC-ReID and CUHK03). In addition, we validate that the proposed PrGCN can be easily embedded into other deep learning architectures to replace Euclidean distance metric and achieve significant performance improvements. (c) 2020 Elsevier B.V. All rights reserved.