A self-training approach for point-supervised object detection and counting in crowds

• Main Authors: Wang, Yi, Hou, Junhui, Hou, Xinyu, Chau, Lap-Pui
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Electrical and electronic engineering; Detectors; Training
• Online Access: https://hdl.handle.net/10356/160520
• Institution: Nanyang Technological University

In this article, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the center points and sizes of crowded objects. Specifically, during training, we uti...