Sample and Computation Redistribution for Efficient Face Detection

TL;DR

This paper introduces data sampling and computation redistribution methods to enhance face detection efficiency and accuracy, achieving state-of-the-art results with lower computational costs on benchmark datasets.

Contribution

It proposes two novel methods, Sample Redistribution and Computation Redistribution, to optimize training data and model computation distribution for face detection.

Findings

SCRFD-34 outperforms TinaFace by 3.86% AP on hard set.

SCRFD-34 is over 3 times faster on GPUs with VGA images.

Achieves superior efficiency-accuracy trade-off on WIDER FACE.

Abstract

Although tremendous strides have been made in uncontrolled face detection, efficient face detection with a low computation cost as well as high precision remains an open challenge. In this paper, we point out that training data sampling and computation distribution strategies are the keys to efficient and accurate face detection. Motivated by these observations, we introduce two simple but effective methods (1) Sample Redistribution (SR), which augments training samples for the most needed stages, based on the statistics of benchmark datasets; and (2) Computation Redistribution (CR), which reallocates the computation between the backbone, neck and head of the model, based on a meticulously defined search methodology. Extensive experiments conducted on WIDER FACE demonstrate the state-of-the-art efficiency-accuracy trade-off for the proposed \scrfd family across a wide range of compute regimes. In particular, \scrfdf{34} outperforms the best competitor, TinaFace, by $3.86\%$ (AP at hard set) while being more than \emph{3$\times$ faster} on GPUs with VGA-resolution images. We also release our code to facilitate future research.