Robust and High Performance Face Detector

TL;DR

This paper presents VIM-FD, a robust and high-performance face detector that leverages advanced neural network techniques and data augmentation to achieve state-of-the-art results on challenging benchmarks.

Contribution

The paper introduces VIM-FD, a face detection method that combines DenseNet-121 backbone, improved data augmentation, attention mechanisms, and strategic training tricks for superior performance.

Findings

Achieves state-of-the-art results on WIDER FACE benchmark.

Outperforms previous face detectors in accuracy and robustness.

Effectively integrates multiple advanced techniques for improved detection.

Abstract

In recent years, face detection has experienced significant performance improvement with the boost of deep convolutional neural networks. In this report, we reimplement the state-of-the-art detector SRN and apply some tricks proposed in the recent literatures to obtain an extremely strong face detector, named VIM-FD. In specific, we exploit more powerful backbone network like DenseNet-121, revisit the data augmentation based on data-anchor-sampling proposed in PyramidBox, and use the max-in-out label and anchor matching strategy in SFD. In addition, we also introduce the attention mechanism to provide additional supervision. Over the most popular and challenging face detection benchmark, i.e., WIDER FACE, the proposed VIM-FD achieves state-of-the-art performance.