Divide and Conquer: Hybrid Pre-training for Person Search

Yanling TIAN, Di Chen, Yunan Liu, Jian Yang, Shanshan Zhang

Abstract:

Large-scale pre-training has proven to be an effective method
for improving performance across different tasks. Current
person search methods use ImageNet pre-trained models for
feature extraction, yet it is not an optimal solution due to the
gap between the pre-training task and person search task (as a
downstream task). Therefore, in this paper, we focus on pre-
training for person search, which involves detecting and re-
identifying individuals simultaneously. Although labeled data
for person search is scarce, datasets for two sub-tasks per-
son detection and re-identification are relatively abundant. To
this end, we propose a hybrid pre-training framework specif-
ically designed for person search using sub-task data only.
It consists of a hybrid learning paradigm that handles data
with different kinds of supervisions, and an intra-task align-
ment module that alleviates domain discrepancy under lim-
ited resources. To the best of our knowledge, this is the first
work that investigates how to support full-task pre-training
using sub-task data. Extensive experiments demonstrate that
our pre-trained model can achieve significant improvements
across diverse protocols, such as person search method, fine-
tuning data, pre-training data and model backbone. For exam-
ple, our model improves ResNet50 based NAE by 10.3% rel-
ative improvement w.r.t. mAP. Our code and pre-trained mod-
els are released for plug-and-play usage to the person search
community.