Volltext-Downloads (blau) und Frontdoor-Views (grau)
The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 1 of 144
Back to Result List

Black-Box Optimization of Object Detector Hyper-Parameters

  • Object detectors have improved considerably in the last years by using advanced Convolutional Neural Networks (CNNs) architectures. However, many detector hyper-parameters are not generally tuned, and they are used with values set by the detector authors. Blackbox optimization methods have gained more attention in recent years because of its ability to optimize the hyper-parameters of various machine learning algorithms and deep learning models. However, these methods are not explored in improving CNN-based object detector's hyper-parameters. In this research work, we propose the use of blackbox optimization methods such as Gaussian Process based Bayesian Optimization (BOGP), Sequential Model-based Algorithm Configuration (SMAC), and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to tune the hyper-parameters in Faster R-CNN and Single Shot MultiBox Detector (SSD). In Faster R-CNN, tuning the input image size, prior box anchor scales and ratios using BOGP, SMAC, and CMA-ES has increased the performance around 1.5% in terms of Mean Average Precision (mAP) on PASCAL VOC. Tuning the anchor scales of SSD has increased the mAP by 3% on PASCAL VOC and marine debris datasets. On the COCO dataset with SSD, mAP improvement is observed in the medium and large objects, but mAP decreases by 1% in small objects. The experimental results show that the blackbox optimization methods have proved to increase the mAP performance by optimizing the object detectors. Moreover, it has achieved better results than the hand-tuned configurations in most of the cases.

Download full text files

Export metadata

Additional Services

Search Google Scholar Check availability

Statistics

Show usage statistics
Metadaten
Document Type:Master's Thesis
Language:English
Author:Mohandass Muthuraja
Number of pages:xvi, 113
ISBN:978-3-96043-082-7
ISSN:1869-5272
URN:urn:nbn:de:hbz:1044-opus-49197
DOI:https://doi.org/10.18418/978-3-96043-082-7
Supervisor:Matias Valdenegro-Toro, Paul G. Plöger, Ralf Thiele, Octavio Arriaga
Publishing Institution:Hochschule Bonn-Rhein-Sieg
Granting Institution:Hochschule Bonn-Rhein-Sieg, Fachbereich Informatik
Contributing Corporation:Bonn-Aachen International Center for Information Technology (b-it); German Research Center for Artificial Intelligence (DFKI), Bremen
Date of first publication:2020/05/29
Series (Volume):Technical Report / Hochschule Bonn-Rhein-Sieg University of Applied Sciences. Department of Computer Science (02-2020)
Keyword:Black-Box Optimization; Computer Vision; Hyper-parameter Tuning; Object Detection; Scale Tuning
Departments, institutes and facilities:Fachbereich Informatik
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Series:Technical Report / University of Applied Sciences Bonn-Rhein-Sieg. Department of Computer Science
Entry in this database:2020/05/29
Licence (Multiple languages):License LogoIn Copyright - Educational Use Permitted (Urheberrechtsschutz - Nutzung zu Bildungszwecken erlaubt)