# Dense Scale Network for Crowd Counting

arXiv: https://arxiv.org/abs/1906.09707 · HTML: https://mlsanity.com/paper/1906.09707/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2019.

## Built on by (most cited first, 12 of 12)

- [Multi-Exit Vision Transformer for Dynamic Inference](https://mlsanity.com/paper/2106.15183/) (2021)
- [Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead](https://mlsanity.com/paper/2105.09121/) (2021)
- [Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation](https://mlsanity.com/paper/2101.12439/) (2021)
- [Deep learning with self-supervision and uncertainty regularization to count fish in underwater images](https://mlsanity.com/paper/2104.14964/) (2021)
- [RGB-T Multi-Modal Crowd Counting Based on Transformer](https://mlsanity.com/paper/2301.03033/) (2023)
- [PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks](https://mlsanity.com/paper/2301.12914/) (2023)
- [Multi-Level Attentive Convoluntional Neural Network for Crowd Counting](https://mlsanity.com/paper/2105.11422/) (2021)
- [Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training](https://mlsanity.com/paper/2208.07075/) (2022)
- [Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimation](https://mlsanity.com/paper/2208.13441/) (2022)
- [Decoupled DETR For Few-shot Object Detection](https://mlsanity.com/paper/2311.11570/) (2023)
- [Accurate Gigapixel Crowd Counting by Iterative Zooming and Refinement](https://mlsanity.com/paper/2305.09271/) (2023)
- [EHNet: An Efficient Hybrid Network for Crowd Counting and Localization](https://mlsanity.com/paper/2503.12061/) (2025)

## Abstract (arXiv)

Crowd counting has been widely studied by computer vision community in recent years. Due to the large scale variation, it remains to be a challenging task. Previous methods adopt either multi-column CNN or single-column CNN with multiple branches to deal with this problem. However, restricted by the number of columns or branches, these methods can only capture a few different scales and have limited capability. In this paper, we propose a simple but effective network called DSNet for crowd counting, which can be easily trained in an end-to-end fashion. The key component of our network is the dense dilated convolution block, in which each dilation layer is densely connected with the others to preserve information from continuously varied scales. The dilation rates in dilation layers are carefully selected to prevent the block from gridding artifacts. To further enlarge the range of scales covered by the network, we cascade three blocks and link them with dense residual connections. We also introduce a novel multi-scale density level consistency loss for performance improvement. To evaluate our method, we compare it with state-of-the-art algorithms on four crowd counting datasets (ShanghaiTech, UCF-QNRF, UCF_CC_50 and UCSD). Experimental results demonstrate that DSNet can achieve the best performance and make significant improvements on all the four datasets (30% on the UCF-QNRF and UCF_CC_50, and 20% on the others).