A deep four-stream convolutional neural network (CNN) is proposed for person re-identification (re-ID) to overcome the poor generalisation of the traditional triplet loss function. Specifically, the proposed method is a four-stream network, taking four input images where two images are from the same identity and the other two are from different identities. The network uses dual identification and verification losses in a single framework to minimise the intra-class distance while maximising the inter-class distance. Extensive experiments illustrate the state-of-the-art performance of the proposed approach on seven challenging person re-ID datasets: VIPeR, CUHK03, CUHK01, PRID2011, i-LIDS, Market-1501, and DukeMTMC-reID. In addition, we build a five-stream network and a four-stream network with an alternate formulation of positive and negative pairs to further explore the performance of the proposed four-stream network. We also demonstrate promising performance when training and testing sets are from different domains, highlighting the real-world applicability of the approach.

提出了一种深四流卷积神经网络（CNN）用于人员重新识别（re-ID），以克服传统三重态损失函数的泛化性差的问题。具体地，所提出的方法是四流网络，其获取四个输入图像，其中两个图像来自相同的身份，另外两个图像来自不同的身份。该网络在单个框架中使用双重标识和验证损失，以最大程度地减少类内距离，同时又使类间距离最大化。大量实验说明了该方法在七个具有挑战性的人员re-ID数据集上的最新性能：VIPeR，CUHK03，CUHK01，PRID2011，i-LIDS，Market-1501和DukeMTMC-reID。此外，我们使用正负对的替代公式构建五流网络和四流网络，以进一步探索建议的四流网络的性能。当训练和测试集来自不同领域时，我们还将展示出令人鼓舞的性能，突出了该方法在现实世界中的适用性。