Deep Ranking Model for Person Re-identification with Pairwise Similarity Comparison

Abstract

This paper presents a deep ranking model with feature learning and fusion supervised by a novel contrastive loss function for person re-identification. Given the probe image set, we organize the training images into a batch of pairwise samples, each probe image with a matched or a mismatched reference from the gallery image set. Treating these pairwise samples as inputs, we build a part-based deep convolutional neural network (CNN) to generate the layered feature representations supervised by the proposed contrastive loss function, in which the intra-class distances are minimized and the inter-class distances are maximized. In the deep model, the feature of different body parts are first discriminately learned in the convolutional layers and then fused in the fully connected layers, which makes it able to extract discriminative features of different individuals. Extensive experiments on the public benchmark datasets are reported to evaluate our method, shown significant improvements on accuracy, as compared with the state-of-the-art approaches.