Deep Feature Learning And Domain Adaptation In Person Re-identification

Person re-identification(re-ID)is a significant technology for video surveillance,which aims to search a target pedestrian appeared in the surveillance network.With growing video data,it is nearly impossible to re-identify a pedestrian only by manpower.Using computer to do the job becomes an urgent matter.Under such circumstance,person re-identification,which is the topic this paper,has become the spot of computer vision.We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.Technically,we contribute a novel fully attentional block which is deeply supervised and can be plugged into any CNN,and a novel curriculum sampling method which is effective for training ranking losses.The learning tasks are integrated into a unified framework and jointly optimized.Experiments have been carried out on Market1501,CUHK03 and DukeMTMC.All the results show that Mancs can significantly outperform the previous state-of-the-arts.In addition,the effectiveness of the newly proposed ideas has been confirmed by extensive ablation studies.Besides,we study the problem of unsupervised domain adaptive re-identification which is an active topic in computer vision but lacks a theoretical foundation.We first extend existing unsupervised domain adaptive classification theories to re-ID tasks.Concretely,we introduce some assumptions on the extracted feature space and then derive several loss functions guided by these assumptions.To optimize them,a novel self-training scheme for unsupervised domain adaptive re-ID tasks is proposed.It iteratively makes guesses for unlabeled target data based on an encoder and trains the encoder based on the guessed labels.Extensive experiments on unsupervised domain adaptive person re-ID and vehicle re-ID tasks with comparisons to the state-of-the-arts confirm the effectiveness of the proposed theories and self-training framework.