Prototype-Guided Saliency Feature Learning for Person Search

Hanjae Kim, Sunghun Joung, Ig-Jae Kim, Kwanghoon Sohn; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 4865-4874


Existing person search methods integrate person detection and re-identification (re-ID) module into a unified system. Though promising results have been achieved, the misalignment problem, which commonly occurs in person search, limits the discriminative feature representation for re-ID. To overcome this limitation, we introduce a novel framework to learn the discriminative representation by utilizing prototype in OIM loss. Unlike conventional methods using prototype as a representation of person identity, we utilize it as guidance to allow the attention network to consistently highlight multiple instances across different poses. Moreover, we propose a new prototype update scheme with adaptive momentum to increase the discriminative ability across different instances. Extensive ablation experiments demonstrate that our method can significantly enhance the feature discriminative power, outperforming the state-of-the-art results on two person search benchmarks including CUHK-SYSU and PRW.

Related Material

@InProceedings{Kim_2021_CVPR, author = {Kim, Hanjae and Joung, Sunghun and Kim, Ig-Jae and Sohn, Kwanghoon}, title = {Prototype-Guided Saliency Feature Learning for Person Search}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {4865-4874} }