Survey for person re-identification based on coarse-to-fine feature learning

Person re-identification (Re-ID), aiming to retrieve interested people through multiple non-overlapping cameras, has caused concerns in pattern recognition communities and computer vision in recent years. With the continuous promotion of deep learning, the research on person Re-ID is more and more extensive. In this paper, we conduct a comprehensive review of the advanced methods and divide them into three categories from coarse to fine: (1) global-based methods, which are based on whole images to obtain discriminative features; (2) part-based methods, which focus on image regions to extract detailed information; (3) multiple granularities-based methods, which combine advantages of the above two categories. For each category, we further classify it according to popular research tools. Then, we give the evaluation of some typical models on a set of benchmark datasets and compare them in detail. We also introduce some widely used training tricks. The methods mentioned in this paper were published in 2011-2021. By discussing their advantages and limitations, we provide a reference for future works.