[论文解读] Going Deeper Into Face Detection: A Survey

Shervin Minaee, Ping Luo+2 more|arXiv (Cornell University)|Mar 27, 2021

Face recognition and analysis参考文献 86被引用 51

一句话总结

基于深度学习的人脸检测方法、架构、数据集、基准和挑战的综合综述，按模型类别组织。

ABSTRACT

Face detection is a crucial first step in many facial recognition and face analysis systems. Early approaches for face detection were mainly based on classifiers built on top of hand-crafted features extracted from local image regions, such as Haar Cascades and Histogram of Oriented Gradients. However, these approaches were not powerful enough to achieve a high accuracy on images of from uncontrolled environments. With the breakthrough work in image classification using deep neural networks in 2012, there has been a huge paradigm shift in face detection. Inspired by the rapid progress of deep learning in computer vision, many deep learning based frameworks have been proposed for face detection over the past few years, achieving significant improvements in accuracy. In this work, we provide a detailed overview of some of the most representative deep learning based face detection methods by grouping them into a few major categories, and present their core architectural designs and accuracies on popular benchmarks. We also describe some of the most popular face detection datasets. Finally, we discuss some current challenges in the field, and suggest potential future research directions.

研究动机与目标

• 回顾从深度学习时代初期到现在的深度学习人脸检测进展。
• 对主要模型家族（Cascade-CNN、RCNN/Faster-RCNN、SSD、FPN、Transformers 等）进行分类与比较。
• 总结广泛使用的人脸检测数据集与评估基准。
• 讨论当前挑战并提出未来研究的潜在方向。

提出的方法

• 基于结构贡献将现有的深度人脸检测工作分为主要类别。
• 提供骨干网络和核心架构思想的概览（CNN、R-CNN、SSD、FPN、GANs 等）。
• 总结每个类别内的关键模型及其主要技术贡献。
• 概述深度人脸检测的流行基准和评估指标。
• 讨论在非受限场景中的挑战并提出未来研究方向。

实验结果

研究问题

• RQ1 用于人脸检测的主要深度学习类别及其核心架构思想有哪些？
• RQ2 骨干架构、损失函数和训练策略如何影响在标准人脸检测基准上的性能？
• RQ3 当前人脸检测研究中哪些数据集和评估指标占主导地位，还有哪些空白？
• RQ4 野外场景人脸检测的主要挑战及潜在应对途径是什么？

主要发现

• 该综述覆盖了跨越多种架构类别的五十多个深度人脸检测模型。
• 它提供了对训练数据、网络骨干、损失函数及训练策略如何带来性能提升的见解。
• 它讨论了流行的基准和指标，以及 FDDB、Wider Face 等数据集的趋势。
• 它强调了姿态、尺度、照明、遮挡等变化带来的挑战，并提出包括基于变换器的方法和上下文建模在内的方向。
• 它强调从 Cascade-CNN 和基于 R-CNN 的方法到单阶段检测器和特征金字塔网络的演变，并关注最近的基于变换器的思路。