Skip to main content

Research Repository

Advanced Search

Toward an ensemble of object detectors.

Dang, Truong; Nguyen, Tien Thanh; McCall, John

Authors

Truong Dang

Profile Image

Professor John McCall j.mccall@rgu.ac.uk
Professorial Lead (NSC) & Lead of the Computational Intelligence Research Group



Contributors

Haiqin Yang
Editor

Kitsuchart Pasupa
Editor

Andrew Chi-Sing Leung
Editor

James T. Kwok
Editor

Jonathan H. Chan
Editor

Irwin King
Editor

Abstract

The field of object detection has witnessed great strides in recent years. With the wave of deep neural networks (DNN), many breakthroughs have achieved for the problems of object detection which previously were thought to be difficult. However, there exists a limitation with DNN-based approaches as some architectures are only suitable for particular types of object. Thus it would be desirable to combine the strengths of different methods to handle objects in different contexts. In this study, we propose an ensemble of object detectors in which individual detectors are adaptively combine for the collaborated decision. The combination is conducted on the outputs of detectors including the predicted label and location for each object. We proposed a detector selection method to select the suitable detectors and a weighted-based combining method to combine the predicted locations of selected detectors. The parameters of these methods are optimized by using Particle Swarm Optimization in order to maximize mean Average Precision (mAP) metric. Experiments conducted on VOC2007 dataset with six object detectors show that our ensemble method is better than each single detector.

Citation

DANG, T., NGUYEN, T.T. and MCCALL, J. 2020. Toward an ensemble of object detectors. In Yang, H., Pasupa, K., Leung, A.C.-S., Kwok, J.T., Chan, J.H. and King, I. (eds.) Neural information processing: proceedings of 27th International conference on neural information processing 2020 (ICONIP 2020), part 5. Communications in computer and information science, 1333. Cham: Springer [online], pages, 458-467. Available from: https://doi.org/10.1007/978-3-030-63823-8_53

Conference Name 27th International conference on neural information processing 2020 (ICONIP 2020)
Conference Location Bangkok, Thailand [virtual conference]
Start Date Nov 18, 2020
End Date Nov 22, 2020
Acceptance Date Aug 15, 2020
Online Publication Date Nov 17, 2020
Publication Date Dec 31, 2020
Deposit Date Dec 15, 2020
Publicly Available Date Dec 15, 2020
Publisher Springer
Pages 458-467
Series Title Communications in computer and information science
Series Number 1333
Series ISSN 1865-0929
Book Title Neural information processing: proceedings of 27th International conference on neural information processing 2020 (ICONIP 2020), Bangkok, Thailand, November 18-22, 2020, part V
ISBN 9783030638221
DOI https://doi.org/10.1007/978-3-030-63823-8_53
Keywords Object detection; Ensemble method; Ensemble learning; Evolutionary computation; Particle swarm optimization
Public URL https://rgu-repository.worktribe.com/output/1005357

Files





You might also like



Downloadable Citations