Person Re-identification through Clustering and Partial Label Smoothing Regularization
Jean-Paul Ainam, Ke Qin, Guisong Liu, Guangchun Luo · 2019
In this paper, we propose a new label smoothing regularization scheme for person re-identification. We first use an unsupervised method for discriminative learning representation. We apply a clustering algorithm on the learned feature to partition the training set into k groups of equal variance and derive a shared space for similar images. Secondly, a GAN model is fed with each cluster to produce samples with relatively similar features to the original space. Our method consists of assigning an adaptive smooth label distribution to each generated sample according to their original cluster. To train our model, we define a new objective function which takes into account the generated samples and fine-tuned a CNN baseline using the objective function. Our model learns to exploit the samples generated by the GAN model to boost the performance of the person re-id by improving generalization. Extensive evaluations were conducted on four large-scale datasets to validate the advantage of the proposed model.