# A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds

arXiv: https://arxiv.org/abs/2007.12831 · HTML: https://mlsanity.com/paper/2007.12831/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2020.

## Built on by (most cited first, 30 of 36)

- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning](https://mlsanity.com/paper/2308.10468/) (2023)
- [Focal Inverse Distance Transform Maps for Crowd Localization](https://mlsanity.com/paper/2102.07925/) (2021)
- [Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance](https://mlsanity.com/paper/2405.10589/) (2024)
- [TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting](https://mlsanity.com/paper/2202.08517/) (2022)
- [Counting Crowds in Bad Weather](https://mlsanity.com/paper/2306.01209/) (2023)
- [Boosting Detection in Crowd Analysis via Underutilized Output Features](https://mlsanity.com/paper/2308.16187/) (2023)
- [Audio-visual Representation Learning for Anomaly Events Detection in Crowds](https://mlsanity.com/paper/2110.14862/) (2021)
- [Scene-Adaptive Attention Network for Crowd Counting](https://mlsanity.com/paper/2112.15509/) (2021)
- [Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher](https://mlsanity.com/paper/2206.05717/) (2022)
- [Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer](https://mlsanity.com/paper/2108.00584/) (2021)
- [Multi-modal Crowd Counting via a Broker Modality](https://mlsanity.com/paper/2407.07518/) (2024)
- [Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization](https://mlsanity.com/paper/2104.12505/) (2021)
- [Multiscale Crowd Counting and Localization By Multitask Point Supervision](https://mlsanity.com/paper/2202.09942/) (2022)
- [Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation](https://mlsanity.com/paper/2206.10075/) (2022)
- [Consistency-Aware Anchor Pyramid Network for Crowd Localization](https://mlsanity.com/paper/2212.04067/) (2022)
- [Learning Discriminative Features for Crowd Counting](https://mlsanity.com/paper/2311.04509/) (2023)
- [Weakly Supervised Attended Object Detection Using Gaze Data as Annotations](https://mlsanity.com/paper/2204.07090/) (2022)
- [SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting](https://mlsanity.com/paper/2311.10011/) (2023)
- [Counting and Locating High-Density Objects Using Convolutional Neural Network](https://mlsanity.com/paper/2102.04366/) (2021)
- [LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds](https://mlsanity.com/paper/2110.04727/) (2021)
- [Mask Focal Loss: A unifying framework for dense crowd counting with canonical object detection networks](https://mlsanity.com/paper/2212.11542/) (2022)
- [Faster Video Moment Retrieval with Point-Level Supervision](https://mlsanity.com/paper/2305.14017/) (2023)
- [3DGeoDet: General-purpose Geometry-aware Image-based 3D Object Detection](https://mlsanity.com/paper/2506.09541/) (2025)
- [Counting with Adaptive Auxiliary Learning](https://mlsanity.com/paper/2203.04061/) (2022)
- [Tree Counting by Bridging 3D Point Clouds with Imagery](https://mlsanity.com/paper/2403.01932/) (2024)
- [3D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinement](https://mlsanity.com/paper/2510.17875/) (2025)
- [Automatic counting of mounds on UAV images: combining instance segmentation and patch-level correction](https://mlsanity.com/paper/2209.02608/) (2022)

## Abstract (arXiv)

In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the center points and sizes of crowded objects. Specifically, during training, we utilize the available point annotations to supervise the estimation of the center points of objects directly. Based on a locally-uniform distribution assumption, we initialize pseudo object sizes from the point-level supervisory information, which are then leveraged to guide the regression of object sizes via a crowdedness-aware loss. Meanwhile, we propose a confidence and order-aware refinement scheme to continuously refine the initial pseudo object sizes such that the ability of the detector is increasingly boosted to detect and count objects in crowds simultaneously. Moreover, to address extremely crowded scenes, we propose an effective decoding method to improve the detector's representation ability. Experimental results on the WiderFace benchmark show that our approach significantly outperforms state-of-the-art point-supervised methods under both detection and counting tasks, i.e., our method improves the average precision by more than 10% and reduces the counting error by 31.2%. Besides, our method obtains the best results on the crowd counting and localization datasets (i.e., ShanghaiTech and NWPU-Crowd) and vehicle counting datasets (i.e., CARPK and PUCPR+) compared with state-of-the-art counting-by-detection methods. The code will be publicly available at https://github.com/WangyiNTU/Point-supervised-crowd-detection.