Sample and Computation Redistribution for Efficient Face Detection
It addresses the problem of high computation cost and low precision in uncontrolled face detection for applications requiring real-time processing, though it is incremental in optimizing existing architectures.
The paper tackles efficient face detection by introducing Sample Redistribution (SR) and Computation Redistribution (CR) methods, achieving a 3.86% improvement in AP on the hard set of WIDER FACE while being over 3x faster than the best competitor.
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.