# Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting

arXiv: https://arxiv.org/abs/2505.21943 · HTML: https://mlsanity.com/paper/2505.21943/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 78 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 30 of 45)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Distribution Matching for Crowd Counting](https://mlsanity.com/paper/2009.13077/) (2020)
- [JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method](https://mlsanity.com/paper/2004.03597/) (2020)
- [Switching Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1708.00199/) (2017)
- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [Localization in the Crowd with Topological Constraints](https://mlsanity.com/paper/2012.12482/) (2020)
- [Domain Generalization via Gradient Surgery](https://mlsanity.com/paper/2108.01621/) (2021)
- [Leveraging Unlabeled Data for Crowd Counting by Learning to Rank](https://mlsanity.com/paper/1803.03095/) (2018)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank](https://mlsanity.com/paper/1902.06285/) (2019)
- [STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning](https://mlsanity.com/paper/2308.10468/) (2023)
- [Point-Query Quadtree for Crowd Counting, Localization, and More](https://mlsanity.com/paper/2308.13814/) (2023)
- [Spatial Uncertainty-Aware Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2107.13271/) (2021)
- [Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks](https://mlsanity.com/paper/2007.03207/) (2020)
- [Training-free Object Counting with Prompts](https://mlsanity.com/paper/2307.00038/) (2023)

## Built on by (most cited first, 6 of 6)

- [Semi-Supervised Multi-View Crowd Counting by Ranking Multi-View Fusion Models](https://mlsanity.com/paper/2512.16243/) (2025)
- [Decoupling What to Count and Where to See for Referring Expression Counting](https://mlsanity.com/paper/2510.24374/) (2025)
- [Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods](https://mlsanity.com/paper/2601.12500/) (2026)
- [Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labeling Budget](https://mlsanity.com/paper/2509.16684/) (2025)
- [FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training](https://mlsanity.com/paper/2602.01540/) (2026)
- [Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting](https://mlsanity.com/paper/2603.16241/) (2026)

## Abstract (arXiv)

Point detection has been developed to locate pedestrians in crowded scenes by training a counter through a point-to-point (P2P) supervision scheme. Despite its excellent localization and counting performance, training a point-based counter still faces challenges concerning annotation labor: hundreds to thousands of points are required to annotate a single sample capturing a dense crowd. In this paper, we integrate point-based methods into a semi-supervised counting framework based on pseudo-labeling, enabling the training of a counter with only a few annotated samples supplemented by a large volume of pseudo-labeled data. However, during implementation, the training encounters issues as the confidence for pseudo-labels fails to be propagated to background pixels via the P2P. To tackle this challenge, we devise a point-specific activation map (PSAM) to visually interpret the phenomena occurring during the ill-posed training. Observations from the PSAM suggest that the feature map is excessively activated by the loss for unlabeled data, causing the decoder to misinterpret these over-activations as pedestrians. To mitigate this issue, we propose a point-to-region (P2R) scheme to substitute P2P, which segments out local regions rather than detects a point corresponding to a pedestrian for supervision. Consequently, pixels in the local region can share the same confidence with the corresponding pseudo points. Experimental results in both semi-supervised counting and unsupervised domain adaptation highlight the advantages of our method, illustrating P2R can resolve issues identified in PSAM. The code is available at https://github.com/Elin24/P2RLoss.