---
title: "Direct Measure Matching for Crowd Counting"
authors:
  - "Hui Lin"
  - "Xiaopeng Hong"
  - "Zhiheng Ma"
  - "Xing Wei"
  - "Yunfeng Qiu"
  - "Yaowei Wang"
  - "Yihong Gong"
doi: "10.24963/ijcai.2021/116"
url: "https://ijcai.org/proceedings/2021/116"
pdf: "https://ijcai.org/proceedings/2021/0116.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "837-844"
track: "Main Track"
keywords:
  - "Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"
  - "Data Mining: Class Imbalance and Unequal Cost"
  - "Constraints and SAT: Constraint Optimization"
---

# Direct Measure Matching for Crowd Counting

Hui Lin, Xiaopeng Hong, Zhiheng Ma, Xing Wei, Yunfeng Qiu, Yaowei Wang, Yihong Gong

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 837-844. DOI: [10.24963/ijcai.2021/116](https://doi.org/10.24963/ijcai.2021/116)

## Abstract

Traditional crowd counting approaches usually use Gaussian assumption to generate pseudo density ground truth, which suffers from problems like inaccurate estimation of the Gaussian kernel sizes. In this paper, we propose a new measure-based counting approach to regress the predicted density maps to the scattered point-annotated ground truth directly. First, crowd counting is formulated as a measure matching problem. Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching. Third, we propose a self-supervised mechanism by devising a Sinkhorn scale consistency loss to resist scale changes. Finally, an efficient optimization method is provided to minimize the overall loss function. Extensive experiments on four challenging crowd counting datasets namely ShanghaiTech, UCF-QNRF, JHU++ and NWPU have validated the proposed method.