论文标题
对象检测器量表的黑盒优化
Black-Box Optimization of Object Detector Scales
论文作者
论文摘要
在过去几年中，对象探测器通过使用高级CNN体系结构有了很大的改善。但是，许多检测器超参数通常是手动调整的，或者它们与检测器作者设置的值一起使用。在改善基于CNN的对象检测器超参数方面，尚未探索自动超参数优化。在这项工作中，我们建议使用黑框优化方法来调整更快的R-CNN和SSD中的先验/默认框尺度，并使用贝叶斯优化，SMAC和CMA-ES调整box缩放。我们表明，通过对Pascal VOC 2007的更快R-CNN地图上的输入图像大小和先前的框锚刻度增加2％，并使用SSD增加3％。在带有SSD的可可数据集上，中型和大对象的MAP改进，但在小物体中，MAP降低了1％。我们还执行回归分析，以找到重大的超参数调整。
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.
