Deeply Associative Two-Stage Representations Learning Based on Labels Interval Extension Loss and Group Loss for Person Re-Identification

Person Re-identification (ReID) aims to match people across non-overlapping camera views in a public space, which is usually regarded as an image retrieval problem to match query images with pedestrian images in the gallery. It is challenging since many difficulties exist such as pose misalignments, occlusions, similar appearance when detecting people. Existing researches on ReID mainly focus on two major problems: representation learning and metric learning. In this paper, we target at learning discriminative representations and make two contributions in total. (i) We propose a novel architecture named Deeply Associative Two-stage Representations Learning (DATRL). It contains the global re-initialization stage and fully-perceptual classification stage employing two identical CNNs associatively at the same time. On the global stage, we take on the backbone of one deep CNN e.g., dozens of layers in the front of Resnet-50 as a normal re-initialization subnetwork. Meanwhile, we apply our own proposed 3D-transpose technique into the backbone of the other CNN to form the 3D-transpose re-initialization subnetwork. The fully-perceptual stage is actually made up of the leftover layers of the original CNNs. On this stage, we take both the global representations learned at multiple hierarchies and the local representations uniformly-partitioned on the highest conv-layer into consideration, and then optimizing them separately for classification. (ii) We introduce a new joint loss function in which our proposed Labels Interval Extension loss (LIEL) and Group loss (GL) are combined to enhance the performance of gradient decent as well as increasing the distances between image features with different identities. We apply the above DATRL, LIEL and GL to ReID thus obtaining DATRL-ReID. Experimental results on four datasets CUHK03, Market-1501, DukeMTMC-reID and MSMT17-V2 demonstrate that DATRL-ReID shows excellent performance in improving recognition accuracy and is superior to state-of-the-art methods.

I. Introduction

Person Re-identification (ReID) aims to search people across non-overlapping surveillance camera views deployed at different locations by matching person images. It has been widely studied in computer vision and pattern recognition communities due to its importance in many safety-critical applications, such as automated video surveillance and forensics including multi-camera tracking, crowded counting and multi-camera activity analysis [1]. Some early approaches used low-level features such as colors, shapes and local descriptors for person appearance representation and employed distance metric learning models as matching functions. With the great success convolutional neural networks (CNN) achieved in many computer vision tasks [2]–[5], deep learning methods have dominated this community, with convincing superiority against hand-crafted competitors [6].