# Learning Error-Driven Curriculum for Crowd Counting

arXiv: https://arxiv.org/abs/2007.09676 · HTML: https://mlsanity.com/paper/2007.09676/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [LCDnet: A Lightweight Crowd Density Estimation Model for Real-time Video Surveillance](https://mlsanity.com/paper/2302.05374/) (2023)
- [SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images](https://mlsanity.com/paper/2407.17956/) (2024)
- [Generalizable Prompt Learning of CLIP: A Brief Overview](https://mlsanity.com/paper/2503.01263/) (2025)
- [Curriculum for Crowd Counting -- Is it Worthy?](https://mlsanity.com/paper/2401.07586/) (2024)
- [Accelerating Deep Learning with Fixed Time Budget](https://mlsanity.com/paper/2410.03790/) (2024)

## Abstract (arXiv)

Density regression has been widely employed in crowd counting. However, the frequency imbalance of pixel values in the density map is still an obstacle to improve the performance. In this paper, we propose a novel learning strategy for learning error-driven curriculum, which uses an additional network to supervise the training of the main network. A tutoring network called TutorNet is proposed to repetitively indicate the critical errors of the main network. TutorNet generates pixel-level weights to formulate the curriculum for the main network during training, so that the main network will assign a higher weight to those hard examples than easy examples. Furthermore, we scale the density map by a factor to enlarge the distance among inter-examples, which is well known to improve the performance. Extensive experiments on two challenging benchmark datasets show that our method has achieved state-of-the-art performance.