Object detectors have improved considerably in the last years by using advanced CNN architectures. However, many detector hyper-parameters are generally manually tuned, or they are used with values set by the detector authors. Automatic Hyper-parameter optimization has not been explored in improving CNN-based object detectors hyper-parameters. In this work, we propose the use of Black-box optimization methods to tune the prior/default box scales in Faster R-CNN and SSD, using Bayesian Optimization, SMAC, and CMA-ES. We show that by tuning the input image size and prior box anchor scale on Faster R-CNN mAP increases by 2% on PASCAL VOC 2007, and by 3% with SSD. On the COCO dataset with SSD there are mAP improvement in the medium and large objects, but mAP decreases by 1% in small objects. We also perform a regression analysis to find the significant hyper-parameters to tune.
@article{arxiv.2010.15823,
title = {Black-Box Optimization of Object Detector Scales},
author = {Mohandass Muthuraja and Octavio Arriaga and Paul Plöger and Frank Kirchner and Matias Valdenegro-Toro},
journal= {arXiv preprint arXiv:2010.15823},
year = {2020}
}