# Towards Using Count-level Weak Supervision for Crowd Counting

arXiv: https://arxiv.org/abs/2003.00164 · HTML: https://mlsanity.com/paper/2003.00164/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Feb 2020.

## Built on by (most cited first, 30 of 33)

- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision](https://mlsanity.com/paper/2205.10203/) (2022)
- [CCTrans: Simplifying and Improving Crowd Counting with Transformer](https://mlsanity.com/paper/2109.14483/) (2021)
- [CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models](https://mlsanity.com/paper/2303.12790/) (2023)
- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification](https://mlsanity.com/paper/2403.09281/) (2024)
- [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024)
- [Rethinking Global Context in Crowd Counting](https://mlsanity.com/paper/2105.10926/) (2021)
- [CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizability](https://mlsanity.com/paper/2203.03768/) (2022)
- [CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP](https://mlsanity.com/paper/2203.08219/) (2022)
- [Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling](https://mlsanity.com/paper/2402.15297/) (2024)
- [Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting](https://mlsanity.com/paper/2203.06388/) (2022)
- [TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image](https://mlsanity.com/paper/2307.06118/) (2023)
- [Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenes](https://mlsanity.com/paper/2310.10352/) (2023)
- [Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting](https://mlsanity.com/paper/2205.14659/) (2022)
- [GCNet: Probing Self-Similarity Learning for Generalized Counting Network](https://mlsanity.com/paper/2302.05132/) (2023)
- [Dense Center-Direction Regression for Object Counting and Localization with Point Supervision](https://mlsanity.com/paper/2408.14457/) (2024)
- [Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting](https://mlsanity.com/paper/2202.10681/) (2022)
- [Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects](https://mlsanity.com/paper/2212.02248/) (2022)
- [Visual Crowd Analysis: Open Research Problems](https://mlsanity.com/paper/2308.10677/) (2023)
- [Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting](https://mlsanity.com/paper/2602.12774/) (2026)
- [Counting with Adaptive Auxiliary Learning](https://mlsanity.com/paper/2203.04061/) (2022)
- [Novel 3D Scene Understanding Applications From Recurrence in a Single Image](https://mlsanity.com/paper/2210.07991/) (2022)
- [Automatic counting of planting microsites via local visual detection and global count estimation](https://mlsanity.com/paper/2311.00796/) (2023)
- [Counting Manatee Aggregations using Deep Neural Networks and Anisotropic Gaussian Kernel](https://mlsanity.com/paper/2311.02315/) (2023)
- [ProgRoCC: A Progressive Approach to Rough Crowd Counting](https://mlsanity.com/paper/2504.13405/) (2025)
- [TCFormer: A 5M-Parameter Transformer with Density-Guided Aggregation for Weakly-Supervised Crowd Counting](https://mlsanity.com/paper/2512.22203/) (2025)
- [Crowd Counting with Sparse Annotation](https://mlsanity.com/paper/2304.06021/) (2023)
- [Vision Transformers for Weakly-Supervised Microorganism Enumeration](https://mlsanity.com/paper/2412.02250/) (2024)

## Abstract (arXiv)

Most existing crowd counting methods require object location-level annotation, i.e., placing a dot at the center of an object. While being simpler than the bounding-box or pixel-level annotation, obtaining this annotation is still labor-intensive and time-consuming especially for images with highly crowded scenes. On the other hand, weaker annotations that only know the total count of objects can be almost effortless in many practical scenarios. Thus, it is desirable to develop a learning method that can effectively train models from count-level annotations. To this end, this paper studies the problem of weakly-supervised crowd counting which learns a model from only a small amount of location-level annotations (fully-supervised) but a large amount of count-level annotations (weakly-supervised). To perform effective training in this scenario, we observe that the direct solution of regressing the integral of density map to the object count is not sufficient and it is beneficial to introduce stronger regularizations on the predicted density map of weakly-annotated images. We devise a simple-yet-effective training strategy, namely Multiple Auxiliary Tasks Training (MATT), to construct regularizes for restricting the freedom of the generated density maps. Through extensive experiments on existing datasets and a newly proposed dataset, we validate the effectiveness of the proposed weakly-supervised method and demonstrate its superior performance over existing solutions.