# AFreeCA: Annotation-Free Counting for All

arXiv: https://arxiv.org/abs/2403.04943 · HTML: https://mlsanity.com/paper/2403.04943/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Is synthetic data from generative models ready for image recognition?](https://mlsanity.com/paper/2210.07574/) (2022)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Differentiation of Blackbox Combinatorial Solvers](https://mlsanity.com/paper/1912.02175/) (2019)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://mlsanity.com/paper/1711.07131/) (2017)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [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)
- [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)
- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion](https://mlsanity.com/paper/2302.03298/) (2023)
- [Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting](https://mlsanity.com/paper/2203.08354/) (2022)
- [A Topological Filter for Learning with Label Noise](https://mlsanity.com/paper/2012.04835/) (2020)
- [Detecting Corrupted Labels Without Training a Model to Predict](https://mlsanity.com/paper/2110.06283/) (2021)
- [Leveraging Unlabeled Data for Crowd Counting by Learning to Rank](https://mlsanity.com/paper/1803.03095/) (2018)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [Behavioral Use Licensing for Responsible AI](https://mlsanity.com/paper/2011.03116/) (2020)
- [NAS-Count: Counting-by-Density with Neural Architecture Search](https://mlsanity.com/paper/2003.00217/) (2020)
- [Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method](https://mlsanity.com/paper/1910.12384/) (2019)
- [Completely Self-Supervised Crowd Counting via Distribution Matching](https://mlsanity.com/paper/2009.06420/) (2020)
- [A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias](https://mlsanity.com/paper/2303.13500/) (2023)

## Built on by (most cited first, 12 of 12)

- [A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches](https://mlsanity.com/paper/2501.19184/) (2025)
- [Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2408.11721/) (2024)
- [CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance](https://mlsanity.com/paper/2508.16644/) (2025)
- [FiGO: Fine-Grained Object Counting without Annotations](https://mlsanity.com/paper/2504.11705/) (2025)
- [Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting](https://mlsanity.com/paper/2605.02752/) (2026)
- [Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localization](https://mlsanity.com/paper/2503.12441/) (2025)
- [Automated Counting of Stacked Objects in Industrial Inspection](https://mlsanity.com/paper/2603.15470/) (2026)
- [The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting](https://mlsanity.com/paper/2605.18063/) (2026)
- [AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Counting](https://mlsanity.com/paper/2607.02139/) (2026)
- [SAM2Auto: Auto Annotation Using FLASH](https://mlsanity.com/paper/2506.07850/) (2025)
- [CountZES: Counting via Zero-Shot Exemplar Selection](https://mlsanity.com/paper/2512.16415/) (2025)
- [RECOUNT: Reference-guided Counting with Synthetic Visual Exemplars](https://mlsanity.com/paper/2608.20621/) (2026)

## Abstract (arXiv)

Object counting methods typically rely on manually annotated datasets. The cost of creating such datasets has restricted the versatility of these networks to count objects from specific classes (such as humans or penguins), and counting objects from diverse categories remains a challenge. The availability of robust text-to-image latent diffusion models (LDMs) raises the question of whether these models can be utilized to generate counting datasets. However, LDMs struggle to create images with an exact number of objects based solely on text prompts but they can be used to offer a dependable textitsorting signal by adding and removing objects within an image. Leveraging this data, we initially introduce an unsupervised sorting methodology to learn object-related features that are subsequently refined and anchored for counting purposes using counting data generated by LDMs. Further, we present a density classifier-guided method for dividing an image into patches containing objects that can be reliably counted. Consequently, we can generate counting data for any type of object and count them in an unsupervised manner. Our approach outperforms other unsupervised and few-shot alternatives and is not restricted to specific object classes for which counting data is available. Code to be released upon acceptance.