# SYRAC: Synthesize, Rank, and Count

arXiv: https://arxiv.org/abs/2310.01662 · HTML: https://mlsanity.com/paper/2310.01662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 2 Oct 2023.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 25 of 25)

- [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)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [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)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [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)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method](https://mlsanity.com/paper/2004.03597/) (2020)
- [Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion](https://mlsanity.com/paper/2302.03298/) (2023)
- [Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels](https://mlsanity.com/paper/2103.13646/) (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)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [Investigating Why Contrastive Learning Benefits Robustness Against Label Noise](https://mlsanity.com/paper/2201.12498/) (2022)
- [Spatial Uncertainty-Aware Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2107.13271/) (2021)
- [Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks](https://mlsanity.com/paper/2007.03207/) (2020)
- [Learning to Count in the Crowd from Limited Labeled Data](https://mlsanity.com/paper/2007.03195/) (2020)
- [Completely Self-Supervised Crowd Counting via Distribution Matching](https://mlsanity.com/paper/2009.06420/) (2020)
- [Active Crowd Counting with Limited Supervision](https://mlsanity.com/paper/2007.06334/) (2020)
- [Document Context Language Models](https://mlsanity.com/paper/1511.03962/) (2015)
- [Towards Partial Supervision for Generic Object Counting in Natural Scenes](https://mlsanity.com/paper/1912.06448/) (2019)

## Abstract (arXiv)

Crowd counting is a critical task in computer vision, with several important applications. However, existing counting methods rely on labor-intensive density map annotations, necessitating the manual localization of each individual pedestrian. While recent efforts have attempted to alleviate the annotation burden through weakly or semi-supervised learning, these approaches fall short of significantly reducing the workload. We propose a novel approach to eliminate the annotation burden by leveraging latent diffusion models to generate synthetic data. However, these models struggle to reliably understand object quantities, leading to noisy annotations when prompted to produce images with a specific quantity of objects. To address this, we use latent diffusion models to create two types of synthetic data: one by removing pedestrians from real images, which generates ranked image pairs with a weak but reliable object quantity signal, and the other by generating synthetic images with a predetermined number of objects, offering a strong but noisy counting signal. Our method utilizes the ranking image pairs for pre-training and then fits a linear layer to the noisy synthetic images using these crowd quantity features. We report state-of-the-art results for unsupervised crowd counting.