# Domain-General Crowd Counting in Unseen Scenarios

arXiv: https://arxiv.org/abs/2212.02573 · HTML: https://mlsanity.com/paper/2212.02573/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 55 references that are in the map.
- First posted on arXiv 5 Dec 2022.

## Builds on (most cited first, 30 of 38)

- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Domain Generalization Using a Mixture of Multiple Latent Domains](https://mlsanity.com/paper/1911.07661/) (2019)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Distribution Matching for Crowd Counting](https://mlsanity.com/paper/2009.13077/) (2020)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [Point in, Box out: Beyond Counting Persons in Crowds](https://mlsanity.com/paper/1904.01333/) (2019)
- [Learning Meta Face Recognition in Unseen Domains](https://mlsanity.com/paper/2003.07733/) (2020)
- [Domain Generalization via Gradient Surgery](https://mlsanity.com/paper/2108.01621/) (2021)
- [Learning Meta-class Memory for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.02958/) (2021)
- [Revisiting Perspective Information for Efficient Crowd Counting](https://mlsanity.com/paper/1807.01989/) (2018)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Crowd Counting with Deep Structured Scale Integration Network](https://mlsanity.com/paper/1908.08692/) (2019)
- [A Style and Semantic Memory Mechanism for Domain Generalization](https://mlsanity.com/paper/2112.07517/) (2021)
- [Cross-View Cross-Scene Multi-View Crowd Counting](https://mlsanity.com/paper/2205.01551/) (2022)
- [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)
- [Crowd counting via scale-adaptive convolutional neural network](https://mlsanity.com/paper/1711.04433/) (2017)
- [Active Crowd Counting with Limited Supervision](https://mlsanity.com/paper/2007.06334/) (2020)
- [Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting](https://mlsanity.com/paper/2004.02133/) (2020)
- [Discrete-Constrained Regression for Local Counting Models](https://mlsanity.com/paper/2207.09865/) (2022)

## Built on by (most cited first, 20 of 20)

- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [Single Domain Generalization for Crowd Counting](https://mlsanity.com/paper/2403.09124/) (2024)
- [DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting](https://mlsanity.com/paper/2308.05311/) (2023)
- [Single Domain Generalization for Few-Shot Counting via Universal Representation Matching](https://mlsanity.com/paper/2505.16778/) (2025)
- [Learning Spatial Similarity Distribution for Few-shot Object Counting](https://mlsanity.com/paper/2405.11770/) (2024)
- [Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2503.17984/) (2025)
- [Video Individual Counting for Moving Drones](https://mlsanity.com/paper/2503.10701/) (2025)
- [Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation](https://mlsanity.com/paper/2404.13992/) (2024)
- [Text-promptable Object Counting via Quantity Awareness Enhancement](https://mlsanity.com/paper/2507.06679/) (2025)
- [Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting](https://mlsanity.com/paper/2602.12774/) (2026)
- [AdaTreeFormer: Few Shot Domain Adaptation for Tree Counting from a Single High-Resolution Image](https://mlsanity.com/paper/2402.02956/) (2024)
- [L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation](https://mlsanity.com/paper/2503.12935/) (2025)
- [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025)
- [Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods](https://mlsanity.com/paper/2601.12500/) (2026)
- [FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting](https://mlsanity.com/paper/2502.10677/) (2025)
- [Towards Conditional Feature Alignment for Cross-Domain Counting](https://mlsanity.com/paper/2506.17137/) (2025)
- [One-Shot Crowd Counting With Density Guidance For Scene Adaptation](https://mlsanity.com/paper/2602.07955/) (2026)
- [Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting](https://mlsanity.com/paper/2603.24106/) (2026)
- [ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation](https://mlsanity.com/paper/2606.23835/) (2026)
- [COBICount: Separating Object and Background Responses for Remote Sensing Object Counting Without Training on Target Data](https://mlsanity.com/paper/2609.39366/) (2026)

## Abstract (arXiv)

Domain shift across crowd data severely hinders crowd counting models to generalize to unseen scenarios. Although domain adaptive crowd counting approaches close this gap to a certain extent, they are still dependent on the target domain data to adapt (e.g. finetune) their models to the specific domain. In this paper, we aim to train a model based on a single source domain which can generalize well on any unseen domain. This falls into the realm of domain generalization that remains unexplored in crowd counting. We first introduce a dynamic sub-domain division scheme which divides the source domain into multiple sub-domains such that we can initiate a meta-learning framework for domain generalization. The sub-domain division is dynamically refined during the meta-learning. Next, in order to disentangle domain-invariant information from domain-specific information in image features, we design the domain-invariant and -specific crowd memory modules to re-encode image features. Two types of losses, i.e. feature reconstruction and orthogonal losses, are devised to enable this disentanglement. Extensive experiments on several standard crowd counting benchmarks i.e. SHA, SHB, QNRF, and NWPU, show the strong generalizability of our method.