An Unsupervised Multi-Shot Person Re-Identification Method via Mutual Normalized Sparse Representation and Stepwise Learning

Due to abundant prior information and widespread applications, multi-shot based person re-identification has drawn increasing attention in recent years. In this paper, the high labeling cast and huge unlabeled data motivate us to focus on the unsupervised scenario and a unified coarse-to-fine framework is proposed, named by Mutual Normalized Sparse Representation (MNSR). Our method is an iteration procedure and each iteration involves two key steps: label estimation and metric model learning. In the former, we present a MNSR model to infer the pairwise labels of cross-camera by endowing sparse representation coefficient with the probability property. MNSR explicitly takes the mutually correlation between cameras into consideration and thus produces more accurate results. Meanwhile, we propose a probability-guided positive pairwise label prediction method to mine hard positive samples. For the latter, we learn a metric model with the estimated pairwise labels as supervision. In this procedure, we select some reliable labels for training by configuring with a stepwise learning method, rather than use all the estimated pair samples. This procedure helps to prevent the noise samples damaging the learning of discriminative metric model, especially for the initial iterations. Extensive experiments are conducted on four publicly available datasets, including PRID 2011, iLIDS-VID, SAIVT-SoftBio and MARS, and the results demonstrate the superior performance of the MNSR method in comparison with state-of-the-art unsupervised multi-shot person re-identification methods.

Automated summary

This paper proposes a unified coarse-to-fine unsupervised person re-identification framework named MNSR, which improves accuracy through Mutual Normalized Sparse Representation model and probability-guided label prediction method. In the metric model learning stage, reliable labels are selected for training to prevent noise samples from affecting the learning process, and experimental results demonstrate the superior performance of the MNSR method.