Hierarchical Pseudo Labeling Based Embranchment Learning for One-Shot Person Re-Identification

Abstract

In this paper, one-shot person re-identification (person re-ID) task is brought into focus, where there is only one labeled sample of each pedestrian. Existing one-shot person re-ID researches usually utilize data insufficiently or treat both labeled and pseudo-labeled data in the same way. To solve these problems, we propose a Hierarchical Pseudo Labeling strategy based on Density and Distance and an Embranchment Learning framework. The pseudo labeling strategy can fully exploit the unlabeled data information and generate accurate pseudo labels by multiple clustering based on pairwise feature distances and distribution densities hierarchically. Our Embranchment Learning framework learns data in an individualized way by feeding data with labels from different sources into distinct network branches paired with personalized loss functions. Besides, Batch Distance Loss and Global Center Loss are designed to target the characteristics of distinct input data. They are capable of distinguishing diverse categories and reducing the intra-class distance respectively. Our method outperforms the existing state-of-the-art algorithm by 36.1, 28.7 of mAP and shortens the training time 6 and 10 epochs on Market-1501 and DukeMTMC-reID respectively.