2020/11/04 by Yuqi Gong, Xuehui Yu, Gong, Yuqi +9 · 5 citations
Computer Science · Engineering · #Advanced Chemical Sensor Technologies #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Data mining #Detector #FOS: Computer and information sciences #Factor (programming language) #Fusion #Object (grammar) #Object detection #Pascal (unit) #Pattern recognition (psychology) #Programming language #Sensor fusion #Telecommunications #cs.CV
paper · pdf · doi:10.48550/arxiv.2011.02298
accepted by WACV2021
openalex publication_date 2020/11/04 · arxiv created 2020/11/09 · arxiv updated 2020/11/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
FPN-based detectors have made significant progress in general object detection, e.g., MS COCO and PASCAL VOC. However, these detectors fail in certain application scenarios, e.g., tiny object detection. In this paper, we argue that the top-down connections between adjacent layers in FPN bring two-side influences for tiny object detection, not only positive. We propose a novel concept, fusion factor, to control information that deep layers deliver to shallow layers, for adapting FPN to tiny object detection. After series of experiments and analysis, we explore how to estimate an effective value of fusion factor for a particular dataset by a statistical method. The estimation is dependent on the number of objects distributed in each layer. Comprehensive experiments are conducted on tiny object detection datasets, e.g., TinyPerson and Tiny CityPersons. Our results show that when configuring FPN with a proper fusion factor, the network is able to achieve significant performance gains over the baseline on tiny object detection datasets. Codes and models will be released.