Anchor-Free Person Search
This work improves efficiency and accuracy for person search, a task relevant to surveillance and security, by introducing a novel anchor-free approach, though it is incremental in adapting existing detection methods.
The paper tackles the problem of person search, which combines pedestrian detection and re-identification, by proposing an anchor-free framework called AlignPS that addresses misalignment issues, resulting in over 20% mAP improvement on CUHK-SYSU and outperforming state-of-the-art two-stage methods with higher speed.
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id). Most existing works employ two-stage detectors like Faster-RCNN, yielding encouraging accuracy but with high computational overhead. In this work, we present the Feature-Aligned Person Search Network (AlignPS), the first anchor-free framework to efficiently tackle this challenging task. AlignPS explicitly addresses the major challenges, which we summarize as the misalignment issues in different levels (i.e., scale, region, and task), when accommodating an anchor-free detector for this task. More specifically, we propose an aligned feature aggregation module to generate more discriminative and robust feature embeddings by following a "re-id first" principle. Such a simple design directly improves the baseline anchor-free model on CUHK-SYSU by more than 20% in mAP. Moreover, AlignPS outperforms state-of-the-art two-stage methods, with a higher speed. Code is available at https://github.com/daodaofr/AlignPS