Single-Fusion Detector: Towards Faster Multi-Scale Object Detection

Arren Matthew C. Antioquia, Daniel Stanley Tan, Arnulfo Azcarraga, Kai-Lung Hua

Research output: Chapter in Book/Report/Conference proceedingConference Article in proceedingAcademicpeer-review

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.
Original languageEnglish
Title of host publication2019 IEEE International Conference on Image Processing (ICIP)
Subtitle of host publicationProceedings
PublisherIEEE
Pages76-80
Number of pages5
ISBN (Electronic)978-1-5386-6249-6
ISBN (Print)978-1-5386-6250-2
DOIs
Publication statusPublished - 26 Aug 2019
Externally publishedYes
EventIEEE International Conference on Image Processing - Taipei, Taiwan, Province of China
Duration: 22 Sept 201925 Sept 2019
https://ieeexplore.ieee.org/xpl/conhome/8791230/proceeding

Conference

ConferenceIEEE International Conference on Image Processing
Abbreviated titleICIP 2019
Country/TerritoryTaiwan, Province of China
CityTaipei
Period22/09/1925/09/19
Internet address

Fingerprint

Dive into the research topics of 'Single-Fusion Detector: Towards Faster Multi-Scale Object Detection'. Together they form a unique fingerprint.

Cite this