# Shallow Feature Based Dense Attention Network for Crowd Counting

arXiv: https://arxiv.org/abs/2006.09853 · HTML: https://mlsanity.com/paper/2006.09853/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 28 of 28)

- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [Spatial Uncertainty-Aware Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2107.13271/) (2021)
- [Calibrating Uncertainty for Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2308.09887/) (2023)
- [Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance](https://mlsanity.com/paper/2405.10589/) (2024)
- [Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting](https://mlsanity.com/paper/2107.12619/) (2021)
- [CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models](https://mlsanity.com/paper/2303.12790/) (2023)
- [Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting](https://mlsanity.com/paper/2108.08023/) (2021)
- [Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation](https://mlsanity.com/paper/2101.12439/) (2021)
- [Interactive Class-Agnostic Object Counting](https://mlsanity.com/paper/2309.05277/) (2023)
- [FGENet: Fine-Grained Extraction Network for Congested Crowd Counting](https://mlsanity.com/paper/2401.01208/) (2024)
- [VMambaCC: A Visual State Space Model for Crowd Counting](https://mlsanity.com/paper/2405.03978/) (2024)
- [Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation](https://mlsanity.com/paper/2509.13939/) (2025)
- [Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation](https://mlsanity.com/paper/2108.02980/) (2021)
- [The Effectiveness of a Simplified Model Structure for Crowd Counting](https://mlsanity.com/paper/2404.07847/) (2024)
- [M"obius Transform for Mitigating Perspective Distortions in Representation Learning](https://mlsanity.com/paper/2405.02296/) (2024)
- [Scale-Aware Network with Regional and Semantic Attentions for Crowd Counting under Cluttered Background](https://mlsanity.com/paper/2101.01479/) (2021)
- [Multi-Scale Context Aggregation Network with Attention-Guided for Crowd Counting](https://mlsanity.com/paper/2104.02245/) (2021)
- [Counting with Adaptive Auxiliary Learning](https://mlsanity.com/paper/2203.04061/) (2022)
- [Multi-scale Feature Aggregation for Crowd Counting](https://mlsanity.com/paper/2208.05256/) (2022)
- [CountEx: Fine-Grained Counting via Exemplars and Exclusion](https://mlsanity.com/paper/2602.19432/) (2026)
- [Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting](https://mlsanity.com/paper/2108.02970/) (2021)
- [Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd Counting](https://mlsanity.com/paper/2206.05475/) (2022)
- [Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network](https://mlsanity.com/paper/2211.06835/) (2022)
- [HDNet: A Hierarchically Decoupled Network for Crowd Counting](https://mlsanity.com/paper/2212.05722/) (2022)
- [Crowd Counting with Sparse Annotation](https://mlsanity.com/paper/2304.06021/) (2023)
- [Scale-Aware Crowd Count Network with Annotation Error Correction](https://mlsanity.com/paper/2312.16771/) (2023)

## Abstract (arXiv)

While the performance of crowd counting via deep learning has been improved dramatically in the recent years, it remains an ingrained problem due to cluttered backgrounds and varying scales of people within an image. In this paper, we propose a Shallow feature based Dense Attention Network (SDANet) for crowd counting from still images, which diminishes the impact of backgrounds via involving a shallow feature based attention model, and meanwhile, captures multi-scale information via densely connecting hierarchical image features. Specifically, inspired by the observation that backgrounds and human crowds generally have noticeably different responses in shallow features, we decide to build our attention model upon shallow-feature maps, which results in accurate background-pixel detection. Moreover, considering that the most representative features of people across different scales can appear in different layers of a feature extraction network, to better keep them all, we propose to densely connect hierarchical image features of different layers and subsequently encode them for estimating crowd density. Experimental results on three benchmark datasets clearly demonstrate the superiority of SDANet when dealing with different scenarios. Particularly, on the challenging UCF CC 50 dataset, our method outperforms other existing methods by a large margin, as is evident from a remarkable 11.9% Mean Absolute Error (MAE) drop of our SDANet.