# Completely Self-Supervised Crowd Counting via Distribution Matching

arXiv: https://arxiv.org/abs/2009.06420 · HTML: https://mlsanity.com/paper/2009.06420/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 22 of 22)

- [CountGD: Multi-Modal Open-World Counting](https://mlsanity.com/paper/2407.04619/) (2024)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [Open-world Text-specified Object Counting](https://mlsanity.com/paper/2306.01851/) (2023)
- [Zero-shot Object Counting with Good Exemplars](https://mlsanity.com/paper/2407.04948/) (2024)
- [LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models](https://mlsanity.com/paper/2412.00686/) (2024)
- [AFreeCA: Annotation-Free Counting for All](https://mlsanity.com/paper/2403.04943/) (2024)
- [Zero-Shot Object Counting with Language-Vision Models](https://mlsanity.com/paper/2309.13097/) (2023)
- [CountGD++: Generalized Prompting for Open-World Counting](https://mlsanity.com/paper/2512.23351/) (2025)
- [Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting](https://mlsanity.com/paper/2205.14659/) (2022)
- [Learning to Count without Annotations](https://mlsanity.com/paper/2307.08727/) (2023)
- [Robust Zero-Shot Crowd Counting and Localization With Adaptive Resolution SAM](https://mlsanity.com/paper/2402.17514/) (2024)
- [ProgRoCC: A Progressive Approach to Rough Crowd Counting](https://mlsanity.com/paper/2504.13405/) (2025)
- [Expanding Zero-Shot Object Counting with Rich Prompts](https://mlsanity.com/paper/2505.15398/) (2025)
- [Counting Through Occlusion: Framework for Open World Amodal Counting](https://mlsanity.com/paper/2511.12702/) (2025)
- [Assessing the Visual Enumeration Abilities of Specialized Counting Architectures and Vision-Language Models](https://mlsanity.com/paper/2512.15254/) (2025)
- [AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Counting](https://mlsanity.com/paper/2607.02139/) (2026)
- [Crowd Counting with Sparse Annotation](https://mlsanity.com/paper/2304.06021/) (2023)
- [Learning from Pseudo-labeled Segmentation for Multi-Class Object Counting](https://mlsanity.com/paper/2307.07677/) (2023)
- [SYRAC: Synthesize, Rank, and Count](https://mlsanity.com/paper/2310.01662/) (2023)
- [FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting](https://mlsanity.com/paper/2502.10677/) (2025)
- [CountZES: Counting via Zero-Shot Exemplar Selection](https://mlsanity.com/paper/2512.16415/) (2025)

## Abstract (arXiv)

Dense crowd counting is a challenging task that demands millions of head annotations for training models. Though existing self-supervised approaches could learn good representations, they require some labeled data to map these features to the end task of density estimation. We mitigate this issue with the proposed paradigm of complete self-supervision, which does not need even a single labeled image. The only input required to train, apart from a large set of unlabeled crowd images, is the approximate upper limit of the crowd count for the given dataset. Our method dwells on the idea that natural crowds follow a power law distribution, which could be leveraged to yield error signals for backpropagation. A density regressor is first pretrained with self-supervision and then the distribution of predictions is matched to the prior by optimizing Sinkhorn distance between the two. Experiments show that this results in effective learning of crowd features and delivers significant counting performance. Furthermore, we establish the superiority of our method in less data setting as well. The code and models for our approach is available at https://github.com/val-iisc/css-ccnn.