# Coarse- and Fine-grained Attention Network with Background-aware Loss for Crowd Density Map Estimation

arXiv: https://arxiv.org/abs/2011.03721 · HTML: https://mlsanity.com/paper/2011.03721/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [Training-free Object Counting with Prompts](https://mlsanity.com/paper/2307.00038/) (2023)
- [Redesigning Multi-Scale Neural Network for Crowd Counting](https://mlsanity.com/paper/2208.02894/) (2022)
- [Scene-Adaptive Attention Network for Crowd Counting](https://mlsanity.com/paper/2112.15509/) (2021)
- [Focus for Free in Density-Based Counting](https://mlsanity.com/paper/2306.05129/) (2023)
- [RGB-T Multi-Modal Crowd Counting Based on Transformer](https://mlsanity.com/paper/2301.03033/) (2023)
- [ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer](https://mlsanity.com/paper/2307.12349/) (2023)
- [Dense Center-Direction Regression for Object Counting and Localization with Point Supervision](https://mlsanity.com/paper/2408.14457/) (2024)
- [ZIP: Scalable Crowd Counting via Zero-Inflated Poisson Modeling](https://mlsanity.com/paper/2506.19955/) (2025)
- [Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting](https://mlsanity.com/paper/2106.12163/) (2021)
- [Counting Manatee Aggregations using Deep Neural Networks and Anisotropic Gaussian Kernel](https://mlsanity.com/paper/2311.02315/) (2023)
- [Indirect-Instant Attention Optimization for Crowd Counting in Dense Scenes](https://mlsanity.com/paper/2206.05648/) (2022)

## Abstract (arXiv)

In this paper, we present a novel method Coarse- and Fine-grained Attention Network (CFANet) for generating high-quality crowd density maps and people count estimation by incorporating attention maps to better focus on the crowd area. We devise a from-coarse-to-fine progressive attention mechanism by integrating Crowd Region Recognizer (CRR) and Density Level Estimator (DLE) branch, which can suppress the influence of irrelevant background and assign attention weights according to the crowd density levels, because generating accurate fine-grained attention maps directly is normally difficult. We also employ a multi-level supervision mechanism to assist the backpropagation of gradient and reduce overfitting. Besides, we propose a Background-aware Structural Loss (BSL) to reduce the false recognition ratio while improving the structural similarity to groundtruth. Extensive experiments on commonly used datasets show that our method can not only outperform previous state-of-the-art methods in terms of count accuracy but also improve the image quality of density maps as well as reduce the false recognition ratio.