Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917246185504768 |
|---|---|
| author | Zou, Yuda Liu, Zelong Gu, Yuliang Du, Bo Xu, Yongchao |
| author_facet | Zou, Yuda Liu, Zelong Gu, Yuliang Du, Bo Xu, Yongchao |
| contents | Crowd counting and localization are important in applications such as public security and traffic management. Existing methods have achieved impressive results thanks to extensive laborious annotations. This paper propose a novel point-localization-based semi-supervised crowd counting and localization method termed Consistent-Point. We identify and address two inconsistencies of pseudo-points, which have not been adequately explored. To enhance their position consistency, we aggregate the positions of neighboring auxiliary proposal-points. Additionally, an instance-wise uncertainty calibration is proposed to improve the class consistency of pseudo-points. By generating more consistent pseudo-points, Consistent-Point provides more stable supervision to the training process, yielding improved results. Extensive experiments across five widely used datasets and three different labeled ratio settings demonstrate that our method achieves state-of-the-art performance in crowd localization while also attaining impressive crowd counting results. The code will be available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12441 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localization Zou, Yuda Liu, Zelong Gu, Yuliang Du, Bo Xu, Yongchao Computer Vision and Pattern Recognition Crowd counting and localization are important in applications such as public security and traffic management. Existing methods have achieved impressive results thanks to extensive laborious annotations. This paper propose a novel point-localization-based semi-supervised crowd counting and localization method termed Consistent-Point. We identify and address two inconsistencies of pseudo-points, which have not been adequately explored. To enhance their position consistency, we aggregate the positions of neighboring auxiliary proposal-points. Additionally, an instance-wise uncertainty calibration is proposed to improve the class consistency of pseudo-points. By generating more consistent pseudo-points, Consistent-Point provides more stable supervision to the training process, yielding improved results. Extensive experiments across five widely used datasets and three different labeled ratio settings demonstrate that our method achieves state-of-the-art performance in crowd localization while also attaining impressive crowd counting results. The code will be available. |
| title | Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12441 |