arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.02236cs.CV
收藏

基于硬负样本的自举人脸检测

Bootstrapping Face Detection with Hard Negative Examples

Xiaomi Inc.(小米公司)

Shaohua Wan, Zhijun Chen, Tao Zhang, Bo Zhang, Kong-kat Wong

摘要:

最近,经过深度训练的卷积网络使人脸检测的性能得到了显着提高。在这份报告中,一种新的方法来训练国家的最先进的人脸检测器。关键是利用硬否定挖掘的思想,并使用从大量背景样本中收集的硬否定来迭代更新基于Faster R-CNN的人脸检测器。我们证明,我们的人脸检测器优于国家的最先进的检测器的FDDB数据集,这是事实标准评估人脸检测算法。

英文摘要:

Recently significant performance improvement in face detection was made possible by deeply trained convolutional networks. In this report, a novel approach for training state-of-the-art face detector is described. The key is to exploit the idea of hard negative mining and iteratively update the Faster R-CNN based face detector with the hard negatives harvested from a large set of background examples. We demonstrate that our face detector outperforms state-of-the-art detectors on the FDDB dataset, which is the de facto standard for evaluating face detection algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑