Saved in:
Bibliographic Details
Main Authors: Pan, Tianhang, Jia, Xiuyi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.16970
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918129642242048
author Pan, Tianhang
Jia, Xiuyi
author_facet Pan, Tianhang
Jia, Xiuyi
contents The motivation of this paper originates from rethinking an essential characteristic of crowd counting: individuals (heads of humans) in the crowd counting task typically occupy a very small portion of the image. This characteristic has never been the focus of existing works: they typically use the same backbone as other visual tasks and pursue a large receptive field. This drives us to propose a new model design principle of crowd counting: emphasizing local modeling capability of the model. We follow the principle and design a crowd counting model named Local Information Matters Model (LIMM). The main innovation lies in two strategies: a window partitioning design that applies grid windows to the model input, and a window-wise contrastive learning design to enhance the model's ability to distinguish between local density levels. Moreover, a global attention module is applied to the end of the model to handle the occasionally occurring large-sized individuals. Extensive experiments on multiple public datasets illustrate that the proposed model shows a significant improvement in local modeling capability (8.7\% in MAE on the JHU-Crowd++ high-density subset for example), without compromising its ability to count large-sized ones, which achieves state-of-the-art performance. Code is available at: https://github.com/tianhangpan/LIMM.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16970
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Local Information Matters: A Rethink of Crowd Counting
Pan, Tianhang
Jia, Xiuyi
Computer Vision and Pattern Recognition
The motivation of this paper originates from rethinking an essential characteristic of crowd counting: individuals (heads of humans) in the crowd counting task typically occupy a very small portion of the image. This characteristic has never been the focus of existing works: they typically use the same backbone as other visual tasks and pursue a large receptive field. This drives us to propose a new model design principle of crowd counting: emphasizing local modeling capability of the model. We follow the principle and design a crowd counting model named Local Information Matters Model (LIMM). The main innovation lies in two strategies: a window partitioning design that applies grid windows to the model input, and a window-wise contrastive learning design to enhance the model's ability to distinguish between local density levels. Moreover, a global attention module is applied to the end of the model to handle the occasionally occurring large-sized individuals. Extensive experiments on multiple public datasets illustrate that the proposed model shows a significant improvement in local modeling capability (8.7\% in MAE on the JHU-Crowd++ high-density subset for example), without compromising its ability to count large-sized ones, which achieves state-of-the-art performance. Code is available at: https://github.com/tianhangpan/LIMM.
title Local Information Matters: A Rethink of Crowd Counting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.16970