Single-fusion detector: Towards faster multi-scale object detection

• Main Authors: Antioquia, Arren Matthew C., Tan, Daniel Stanley, Azcarraga, Arnulfo, Hua, Kai Lung
• Format: text
• Published: Animo Repository 2019
• Subjects: Image converters; Neural networks (Computer science); Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/3022
• Institution: De La Salle University

Despite recent improvements, the arbitrary sizes of objects still impede the predictive ability of object detectors. Recent solutions combine feature maps of different receptive fields to detect multi-scale objects. However, these methods have large computational costs resulting to slower inference time, which is not practical for real-time applications. Contrarily, fusion methods depending on large networks with many skip connections demand larger memory requirement, prohibiting usage in devices with limited memory. In this paper, we propose a more computationally efficient fusion method which integrates higher-order information to low-level feature maps using a single operation. Our method can flexibly adapt to any base network, allowing tailored performance for different computational requirements. Our approach achieves 81.7% mAP at 41 FPS on the PASCAL VOC dataset using ResNet-50 as the base network, which is superior in terms of both speed and mAP as compared to several state-of-the-art baselines, even those which use larger base networks. © 2019 IEEE.