Hierarchical Distillation Learning for Scalable Person Search

Abstract Existing person search methods typically focus on improving person detection accuracy. This ignores the model inference efficiency, which however is fundamentally significant for real-world applications. In this work, we address this limitation by investigating the scalability problem of person search involving both model accuracy and inference efficiency simultaneously. Specifically, we formulate a Hierarchical Distillation Learning (HDL) approach. With HDL, we aim to comprehensively distil the knowledge of a strong teacher model with strong learning capability to a lightweight student model with weak learning capability. To facilitate the HDL process, we design a simple and powerful teacher model for joint learning of person detection and person re-identification matching in unconstrained scene images. Extensive experiments show the modelling advantages and cost-effectiveness superiority of HDL over the state-of-the-art person search methods on three large person search benchmarks: CUHK-SYSU, PRW, and DukeMTMC-PS.