Modeling Noisy Annotations for Crowd Counting

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

60 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationNeurIPS Proceedings
Subtitle of host publicationAdvances in Neural Information Processing Systems 33 (NeurIPS 2020)
EditorsH. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, H. Lin
Volume33
Publication statusPublished - Dec 2020

Conference

Title34th Conference on Neural Information Processing Systems (NeurIPS 2020)
LocationVirtual
PlaceCanada
CityVancouver
Period6 - 12 December 2020

Abstract

The annotation noise in crowd counting is not modeled in traditional crowd counting algorithms based on crowd density maps. In this paper, we first model the annotation noise using a random variable with Gaussian distribution, and derive the pdf of the crowd density value for each spatial location in the image. We then approximate the joint distribution of the density values (i.e., the distribution of density maps) with a full covariance multivariate Gaussian density, and derive a low-rank approximate for tractable implementation. We use our loss function to train a crowd density map estimator and achieve state-of-the-art performance on three large-scale crowd counting datasets, which confirms its effectiveness. Examination of the predictions of the trained model shows that it can correctly predict the locations of people in spite of the noisy training data, which demonstrates the robustness of our loss function to annotation noise.

Citation Format(s)

Modeling Noisy Annotations for Crowd Counting. / Wan, Jia; Chan, Antoni B.
NeurIPS Proceedings: Advances in Neural Information Processing Systems 33 (NeurIPS 2020). ed. / H. Larochelle; M. Ranzato; R. Hadsell; M.F. Balcan; H. Lin. Vol. 33 2020.

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