Bootstrapping Face Detection with Hard Negative Examples

Abstract

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.

References in corpus (2)

• Face Detection with the Faster R-CNN
• Is Faster R-CNN Doing Well for Pedestrian Detection?

Cited by in corpus (8)

• Object Detection with Deep Learning: A Review
• Detect Faces Efficiently: A Survey and Evaluations
• S${}^3$FD: Single Shot Scale-invariant Face Detector
• Face Detection using Deep Learning: An Improved Faster RCNN Approach
• RefineFace: Refinement Neural Network for High Performance Face Detection
• Unsupervised Hard Example Mining from Videos for Improved Object Detection
• Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation
• MSFD:Multi-Scale Receptive Field Face Detector