Single-fusion detector: Towards faster multi-scale object detection
College
College of Computer Studies
Department/Unit
Computer Science
Document Type
Dissertation
Publication Date
3-1-2019
Abstract
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.
html
Recommended Citation
Antioquia, A. C. (2019). Single-fusion detector: Towards faster multi-scale object detection. Retrieved from https://animorepository.dlsu.edu.ph/faculty_research/5763
Disciplines
Computer Sciences
Keywords
Image converters; Neural networks (Computer science)
Upload File
wf_no