2020/07/19 by Wenxi Li, Zhuoqun Cao, Li, Wenxi +7
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Data Stream Mining Techniques #FOS: Computer and information sciences #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2007.09676
openalex publication_date 2020/07/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.