Bootstrapping Face Detection with Hard Negative Examples

TL;DR

This paper introduces a novel training approach for face detection that leverages hard negative mining with Faster R-CNN, resulting in improved performance on standard benchmarks.

Contribution

The paper presents a new training method using hard negative mining to enhance face detector accuracy beyond existing state-of-the-art methods.

Findings

Outperforms existing face detectors on FDDB dataset

Effectively utilizes hard negative examples for training

Improves detection accuracy with iterative training process

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.