A Generalized Loss Function for Crowd Counting and Localization

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

131 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Subtitle of host publicationCVPR 2021
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Pages1974-1983
ISBN (electronic)9781665445092
ISBN (print)9781665445108
Publication statusPublished - 2021

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919
ISSN (electronic)2575-7075

Conference

Title2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)
LocationVirtual
Period19 - 25 June 2021

Abstract

Previous work [40] shows that a better density map representation can improve the performance of crowd counting. In this paper, we investigate learning the density map representation through an unbalanced optimal transport problem, and propose a generalized loss function to learn density maps for crowd counting and localization. We prove that pixel-wise L2 loss and Bayesian loss [29] are special cases and suboptimal solutions to our proposed loss function. A perspective-guided transport cost function is further proposed to better handle the perspective transformation in crowd images. Since the predicted density will be pushed toward annotation positions, the density map prediction will be sparse and can naturally be used for localization. Finally, the proposed loss outperforms other losses on four large-scale datasets for counting, and achieves the best localization performance on NWPU-Crowd and UCF-QNRF.

Citation Format(s)

A Generalized Loss Function for Crowd Counting and Localization. / Wan, Jia; Liu, Ziquan; Chan, Antoni B.
Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2021. Institute of Electrical and Electronics Engineers, Inc., 2021. p. 1974-1983 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review