# Bootstrapping Face Detection with Hard Negative Examples

arXiv: https://arxiv.org/abs/1608.02236 · HTML: https://mlsanity.com/paper/1608.02236/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2016.

## Built on by (most cited first, 6 of 6)

- [YoChameleon: Personalized Vision and Language Generation](https://mlsanity.com/paper/2504.20998/) (2025)
- [Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss](https://mlsanity.com/paper/2402.06187/) (2024)
- [Detect Faces Efficiently: A Survey and Evaluations](https://mlsanity.com/paper/2112.01787/) (2021)
- [An Artificial Intelligence Dataset for Solar Energy Locations in India](https://mlsanity.com/paper/2202.01340/) (2022)
- [Global Renewables Watch: A Temporal Dataset of Solar and Wind Energy Derived from Satellite Imagery](https://mlsanity.com/paper/2503.14860/) (2025)
- [ProjB: An Improved Bilinear Biased ProjE model for Knowledge Graph Completion](https://mlsanity.com/paper/2209.02390/) (2022)

## Abstract (arXiv)

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.