TY  - THES
U1  - Master Thesis
A1  - Muthuraja, Mohandass
T1  - Black-Box Optimization of Object Detector Hyper-Parameters
N2  - 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.
T3  - Technical Report / Hochschule Bonn-Rhein-Sieg University of Applied Sciences. Department of Computer Science - 02-2020 
KW  - Object Detection
KW  - Hyper-parameter Tuning
KW  - Black-Box Optimization
KW  - Computer Vision
KW  - Scale Tuning
UN  - https://nbn-resolving.org/urn:nbn:de:hbz:1044-opus-49197
SN  - 1869-5272
SS  - 1869-5272
SN  - 978-3-96043-082-7
SB  - 978-3-96043-082-7
U6  - https://doi.org/10.18418/978-3-96043-082-7
DO  - https://doi.org/10.18418/978-3-96043-082-7
SP  - xvi, 113
S1  - xvi, 113
ER  -