# Count2Density: Crowd Density Estimation without Location-level Annotations

arXiv: https://arxiv.org/abs/2509.03170 · HTML: https://mlsanity.com/paper/2509.03170/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 42 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Builds on (most cited first, 28 of 28)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [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)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method](https://mlsanity.com/paper/2004.03597/) (2020)
- [Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection](https://mlsanity.com/paper/1708.02001/) (2017)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.03770/) (2023)
- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [Leveraging Unlabeled Data for Crowd Counting by Learning to Rank](https://mlsanity.com/paper/1803.03095/) (2018)
- [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)
- [Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks](https://mlsanity.com/paper/2007.03207/) (2020)
- [Towards Using Count-level Weak Supervision for Crowd Counting](https://mlsanity.com/paper/2003.00164/) (2020)
- [Learning to Count in the Crowd from Limited Labeled Data](https://mlsanity.com/paper/2007.03195/) (2020)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Texture-guided Saliency Distilling for Unsupervised Salient Object Detection](https://mlsanity.com/paper/2207.05921/) (2022)
- [Calibrating Uncertainty for Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2308.09887/) (2023)
- [Active Crowd Counting with Limited Supervision](https://mlsanity.com/paper/2007.06334/) (2020)
- [Focus on Semantic Consistency for Cross-domain Crowd Understanding](https://mlsanity.com/paper/2002.08623/) (2020)
- [Crowd Counting via Perspective-Guided Fractional-Dilation Convolution](https://mlsanity.com/paper/2107.03665/) (2021)
- [Bi-level Alignment for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2205.05844/) (2022)
- [Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting](https://mlsanity.com/paper/2203.06388/) (2022)
- [Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting](https://mlsanity.com/paper/2205.14659/) (2022)

## Abstract (arXiv)

Crowd density estimation is a well-known computer vision task aimed at estimating the density distribution of people in an image. The main challenge in this domain is the reliance on fine-grained location-level annotations, (i.e. points placed on top of each individual) to train deep networks. Collecting such detailed annotations is both tedious, time-consuming, and poses a significant barrier to scalability for real-world applications. To alleviate this burden, we present Count2Density: a novel pipeline designed to predict meaningful density maps containing quantitative spatial information using only count-level annotations (i.e., total number of people) during training. To achieve this, Count2Density generates pseudo-density maps leveraging past predictions stored in a Historical Map Bank, thereby reducing confirmation bias. This bank is initialised using an unsupervised saliency estimator to provide an initial spatial prior and is iteratively updated with an EMA of predicted density maps. These pseudo-density maps are obtained by sampling locations from estimated crowd areas using a hypergeometric distribution, with the number of samplings determined by the count-level annotations. To further enhance the spatial awareness of the model, we add a self-supervised contrastive spatial regulariser to encourage similar feature representations within crowded regions while maximising dissimilarity with background regions. Experimental results demonstrate that our approach significantly outperforms cross-domain adaptation methods and achieves better results than recent state-of-the-art approaches in semi-supervised settings across several datasets. Additional analyses validate the effectiveness of each individual component of our pipeline, confirming the ability of Count2Density to effectively retrieve spatial information from count-level annotations and enabling accurate subregion counting.