Abstract: To reduce the impact of supervised learning requiring a large amount of high -quality labeled data, a semi-supervised pedestrian re -identification method based on regularization constraint is proposed. This method constructs a dual -model network with the same initialization parameters, namely the teacher network and the student network. During the training process, some labeled data and a large amount of unlabeled data are randomly used as the input of the dual model, and the parameters of the dual model network are constrained by regularization, so that the output results of the same labeled or unlabeled input data remain consistent. On this basis, the teacher network uses the stochastic gradient descent method to optimize the required parameters, and the student network uses the parameters optimized by the teacher network to perform the weighted moving average iteration to obtain the required parameters. The experimental results show that the Rank-1 and mAP of the proposed method on the market1501 dataset with partial labels and a large number of unlabeled data sets are improved compared with the Rank-1 and mAP of the original ABD-Net method, which proves that this algorithm is effective by learning with a small number of labels.

Key words: pedestrian re-identification, semi-supervised learning, regularization constraint, deep learning