# One-Shot Crowd Counting With Density Guidance For Scene Adaptation

arXiv: https://arxiv.org/abs/2602.07955 · HTML: https://mlsanity.com/paper/2602.07955/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Builds on (most cited first, 30 of 31)

- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [Prototype Mixture Models for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2008.03898/) (2020)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection](https://mlsanity.com/paper/2405.10300/) (2024)
- [Switchable Whitening for Deep Representation Learning](https://mlsanity.com/paper/1904.09739/) (2019)
- [Few-shot Object Counting with Similarity-Aware Feature Enhancement](https://mlsanity.com/paper/2201.08959/) (2022)
- [DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting](https://mlsanity.com/paper/2404.16622/) (2024)
- [DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection](https://mlsanity.com/paper/2404.09216/) (2024)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting](https://mlsanity.com/paper/2312.16580/) (2023)
- [CNN-based Density Estimation and Crowd Counting: A Survey](https://mlsanity.com/paper/2003.12783/) (2020)
- [Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2204.10638/) (2022)
- [Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark](https://mlsanity.com/paper/2105.02440/) (2021)
- [Attentive Crowd Flow Machines](https://mlsanity.com/paper/1809.00101/) (2018)
- [Crowd Counting using Deep Recurrent Spatial-Aware Network](https://mlsanity.com/paper/1807.00601/) (2018)
- [Domain-General Crowd Counting in Unseen Scenarios](https://mlsanity.com/paper/2212.02573/) (2022)
- [Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN](https://mlsanity.com/paper/1807.09993/) (2018)
- [T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting](https://mlsanity.com/paper/2502.20625/) (2025)
- [Single Domain Generalization for Crowd Counting](https://mlsanity.com/paper/2403.09124/) (2024)
- [FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models](https://mlsanity.com/paper/2410.04810/) (2024)
- [Ten Years of Pedestrian Detection, What Have We Learned?](https://mlsanity.com/paper/1411.4304/) (2014)
- [DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting](https://mlsanity.com/paper/2308.05311/) (2023)
- [Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning](https://mlsanity.com/paper/2002.00264/) (2020)
- [Semantic Generative Augmentations for Few-Shot Counting](https://mlsanity.com/paper/2311.16122/) (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)

## Abstract (arXiv)

Crowd scenes captured by cameras at different locations vary greatly, and existing crowd models have limited generalization for unseen surveillance scenes. To improve the generalization of the model, we regard different surveillance scenes as different category scenes, and introduce few-shot learning to make the model adapt to the unseen surveillance scene that belongs to the given exemplar category scene. To this end, we propose to leverage local and global density characteristics to guide the model of crowd counting for unseen surveillance scenes. Specifically, to enable the model to adapt to the varying density variations in the target scene, we propose the multiple local density learner to learn multi prototypes which represent different density distributions in the support scene. Subsequently, these multiple local density similarity matrixes are encoded. And they are utilized to guide the model in a local way. To further adapt to the global density in the target scene, the global density features are extracted from the support image, then it is used to guide the model in a global way. Experiments on three surveillance datasets shows that proposed method can adapt to the unseen surveillance scene and outperform recent state-of-the-art methods in the few-shot crowd counting.