# Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation

arXiv: https://arxiv.org/abs/2206.10075 · HTML: https://mlsanity.com/paper/2206.10075/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 102 references that are in the map.
- First posted on arXiv 21 Jun 2022.

## Builds on (most cited first, 30 of 62)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges](https://mlsanity.com/paper/2102.12219/) (2021)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [How Much Position Information Do Convolutional Neural Networks Encode?](https://mlsanity.com/paper/2001.08248/) (2020)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [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)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [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)
- [An Attention Free Transformer](https://mlsanity.com/paper/2105.14103/) (2021)
- [JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method](https://mlsanity.com/paper/2004.03597/) (2020)
- [Switching Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1708.00199/) (2017)
- [A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning](https://mlsanity.com/paper/1609.04453/) (2016)
- [Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection](https://mlsanity.com/paper/1906.07538/) (2019)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)

## Built on by (most cited first, 8 of 8)

- [Learning Discriminative Features for Crowd Counting](https://mlsanity.com/paper/2311.04509/) (2023)
- [Diffusion-based Data Augmentation for Object Counting Problems](https://mlsanity.com/paper/2401.13992/) (2024)
- [Progressive Multi-resolution Loss for Crowd Counting](https://mlsanity.com/paper/2212.04127/) (2022)
- [The Effectiveness of a Simplified Model Structure for Crowd Counting](https://mlsanity.com/paper/2404.07847/) (2024)
- [L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation](https://mlsanity.com/paper/2503.12935/) (2025)
- [mmCounter: Static People Counting in Dense Indoor Scenarios Using mmWave Radar](https://mlsanity.com/paper/2512.10357/) (2025)
- [Constrained Gaussian Process Motion Planning via Stein Variational Newton Inference](https://mlsanity.com/paper/2504.04936/) (2025)
- [Dense Point-to-Mask Optimization with Reinforced Point Selection for Crowd Instance Segmentation](https://mlsanity.com/paper/2604.01742/) (2026)

## Abstract (arXiv)

In real-world crowd counting applications, the crowd densities in an image vary greatly. When facing density variation, humans tend to locate and count the targets in low-density regions, and reason the number in high-density regions. We observe that CNN focus on the local information correlation using a fixed-size convolution kernel and the Transformer could effectively extract the semantic crowd information by using the global self-attention mechanism. Thus, CNN could locate and estimate crowds accurately in low-density regions, while it is hard to properly perceive the densities in high-density regions. On the contrary, Transformer has a high reliability in high-density regions, but fails to locate the targets in sparse regions. Neither CNN nor Transformer can well deal with this kind of density variation. To address this problem, we propose a CNN and Transformer Adaptive Selection Network (CTASNet) which can adaptively select the appropriate counting branch for different density regions. Firstly, CTASNet generates the prediction results of CNN and Transformer. Then, considering that CNN/Transformer is appropriate for low/high-density regions, a density guided adaptive selection module is designed to automatically combine the predictions of CNN and Transformer. Moreover, to reduce the influences of annotation noise, we introduce a Correntropy based optimal transport loss. Extensive experiments on four challenging crowd counting datasets have validated the proposed method.