In this paper, we propose a lightweight and accurate face detection algorithm
LAFD (Light and accurate face detection) based on Retinaface. Backbone network
in the algorithm is a modified MobileNetV3 network which adjusts the size of
the convolution kernel, the channel expansion multiplier of the inverted
residuals block and the use of the SE attention mechanism. Deformable
convolution network(DCN) is introduced in the context module and the algorithm
uses focal loss function instead of cross-entropy loss function as the
classification loss function of the model. The test results on the WIDERFACE
dataset indicate that the average accuracy of LAFD is 94.1%, 92.2% and 82.1%
for the "easy", "medium" and "hard" validation subsets respectively with an
improvement of 3.4%, 4.0% and 8.3% compared to Retinaface and 3.1%, 4.1% and
4.1% higher than the well-performing lightweight model, LFFD. If the input
image is pre-processed and scaled to 1560px in length or 1200px in width, the
model achieves an average accuracy of 86.2% on the 'hard' validation subset.
The model is lightweight, with a size of only 10.2MB.

本研究提出了一种轻量且准确的面部检测算法 LAFD（基于 Retinaface）。该算法中的主干网络是修改的 MobileNetV3 网络，调整了卷积核的大小、反向残差块的通道扩展乘数以及 SE 注意机制的使用。在上下文模块中引入了可变形卷积网络（DCN），并使用焦点损失函数作为模型的分类损失函数，而不是交叉熵损失函数。在 WIDERFACE 数据集上的测试结果表明，LAFD 的平均准确率分别为 94.1％，92.2％和 82.1％，对应于 “easy”，“medium” 和 “hard” 验证子集，相对于 Retinaface 分别提高了 3.4％，4.0％和 8.3％，相对于轻量级模型 LFFD 分别提高了 3.1％，4.1％和 4.1％。如果将输入图像预处理并缩放到 1560 像素的长度或 1200 像素的宽度，该模型在 “hard” 验证子集上可以达到 86.2％的平均准确率。该模型很轻量，仅有 10.2MB 的大小。

一种基于 Retinaface 的轻量级和准确的人脸检测算法

A Lightweight and Accurate Face Detection Algorithm Based on Retinaface

Though tremendous strides have been made in uncontrolled face detection,
accurate and efficient face localisation in the wild remains an open challenge.
This paper presents a robust single-stage face detector, named RetinaFace,
which performs pixel-wise face localisation on various scales of faces by
taking advantages of joint extra-supervised and self-supervised multi-task
learning. Specifically, We make contributions in the following five aspects:
(1) We manually annotate five facial landmarks on the WIDER FACE dataset and
observe significant improvement in hard face detection with the assistance of
this extra supervision signal. (2) We further add a self-supervised mesh
decoder branch for predicting a pixel-wise 3D shape face information in
parallel with the existing supervised branches. (3) On the WIDER FACE hard test
set, RetinaFace outperforms the state of the art average precision (AP) by 1.1%
(achieving AP equal to 91.4%). (4) On the IJB-C test set, RetinaFace enables
state of the art methods (ArcFace) to improve their results in face
verification (TAR=89.59% for FAR=1e-6). (5) By employing light-weight backbone
networks, RetinaFace can run real-time on a single CPU core for a
VGA-resolution image. Extra annotations and code have been made available at:
this https URL

本文介绍了一种名为 RetinaFace 的检测器，采用联合额外监督和自监督多任务学习，在各种尺度的人脸上实现了像素级别的人脸定位，并采用 5 个额外的面部标记，取得了显著的性能提升。