# Deep Density-aware Count Regressor

arXiv: https://arxiv.org/abs/1908.03314 · HTML: https://mlsanity.com/paper/1908.03314/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [LCDnet: A Lightweight Crowd Density Estimation Model for Real-time Video Surveillance](https://mlsanity.com/paper/2302.05374/) (2023)
- [Crowd Counting in Harsh Weather using Image Denoising with Pix2Pix GANs](https://mlsanity.com/paper/2310.07245/) (2023)
- [Multimodal Crowd Counting with Pix2Pix GANs](https://mlsanity.com/paper/2401.07591/) (2024)
- [Crowd Density Estimation using Imperfect Labels](https://mlsanity.com/paper/2212.01450/) (2022)
- [Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting](https://mlsanity.com/paper/2311.11974/) (2023)

## Abstract (arXiv)

We seek to improve crowd counting as we perceive limits of currently prevalent density map estimation approach on both prediction accuracy and time efficiency. We leverage multilevel pixelation of density map as it helps improve SNR of training data and therefore, reduce prediction error. To achieve a better model, we introduce multilayer gradient fusion for training a density-aware global count regressor. More specifically, on training stage, a backbone network receives gradients from multiple branches to learn the density information, whereas those branches are to be detached to accelerate inference. By taking advantages of such method, our model improves benchmark results on public datasets and exhibits itself to be a new solution to crowd counting problems in practice.