# FGENet: Fine-Grained Extraction Network for Congested Crowd Counting

arXiv: https://arxiv.org/abs/2401.01208 · HTML: https://mlsanity.com/paper/2401.01208/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 2 Jan 2024.

## Builds on (most cited first, 19 of 19)

- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [Improving Deep Regression with Ordinal Entropy](https://mlsanity.com/paper/2301.08915/) (2023)
- [CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting](https://mlsanity.com/paper/1707.09605/) (2017)
- [Spatial Uncertainty-Aware Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2107.13271/) (2021)
- [Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark](https://mlsanity.com/paper/2105.02440/) (2021)
- [Shallow Feature Based Dense Attention Network for Crowd Counting](https://mlsanity.com/paper/2006.09853/) (2020)
- [Direct Measure Matching for Crowd Counting](https://mlsanity.com/paper/2107.01558/) (2021)
- [Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1909.07608/) (2019)
- [FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion](https://mlsanity.com/paper/2202.13660/) (2022)
- [Centralized Feature Pyramid for Object Detection](https://mlsanity.com/paper/2210.02093/) (2022)
- [Cross-head Supervision for Crowd Counting with Noisy Annotations](https://mlsanity.com/paper/2303.09245/) (2023)

## Built on by (most cited first, 7 of 7)

- [VMambaCC: A Visual State Space Model for Crowd Counting](https://mlsanity.com/paper/2405.03978/) (2024)
- [EHNet: An Efficient Hybrid Network for Crowd Counting and Localization](https://mlsanity.com/paper/2503.12061/) (2025)
- [Local Information Matters: A Rethink of Crowd Counting](https://mlsanity.com/paper/2508.16970/) (2025)
- [RT-Counter: Real-Time Text-Guided Open-Vocabulary Object Counting](https://mlsanity.com/paper/2606.17561/) (2026)
- [Test-Time Training for Robust Text-Guided Open-Vocabulary Object Counting](https://mlsanity.com/paper/2606.17601/) (2026)
- [MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality Block](https://mlsanity.com/paper/2606.17650/) (2026)
- [Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting](https://mlsanity.com/paper/2606.18566/) (2026)

## Abstract (arXiv)

Crowd counting has gained significant popularity due to its practical applications. However, mainstream counting methods ignore precise individual localization and suffer from annotation noise because of counting from estimating density maps. Additionally, they also struggle with high-density images.To address these issues, we propose an end-to-end model called Fine-Grained Extraction Network (FGENet). Different from methods estimating density maps, FGENet directly learns the original coordinate points that represent the precise localization of individuals.This study designs a fusion module, named Fine-Grained Feature Pyramid(FGFP), that is used to fuse feature maps extracted by the backbone of FGENet. The fused features are then passed to both regression and classification heads, where the former provides predicted point coordinates for a given image, and the latter determines the confidence level for each predicted point being an individual. At the end, FGENet establishes correspondences between prediction points and ground truth points by employing the Hungarian algorithm. For training FGENet, we design a robust loss function, named Three-Task Combination (TTC), to mitigate the impact of annotation noise. Extensive experiments are conducted on four widely used crowd counting datasets. Experimental results demonstrate the effectiveness of FGENet. Notably, our method achieves a remarkable improvement of 3.14 points in Mean Absolute Error (MAE) on the ShanghaiTech Part A dataset, showcasing its superiority over the existing state-of-the-art methods. Even more impressively, FGENet surpasses previous benchmarks on the UCFCC50 dataset with an astounding enhancement of 30.16 points in MAE.