YOLO5Face: Why Reinventing a Face Detector

TL;DR

This paper introduces YOLO5Face, a face detector based on YOLOv5, optimized for face detection with several modifications, achieving state-of-the-art results on the WiderFace dataset across various model sizes.

Contribution

The paper presents a modified YOLOv5 architecture tailored for face detection, including new components like a landmark head and input stem, with models suitable for different deployment scenarios.

Findings

Achieves state-of-the-art performance on WiderFace dataset

Effective across multiple model sizes from large to small

Outperforms specialized face detectors on VGA images

Abstract

Tremendous progress has been made on face detection in recent years using convolutional neural networks. While many face detectors use designs designated for detecting faces, we treat face detection as a generic object detection task. We implement a face detector based on the YOLOv5 object detector and call it YOLO5Face. We make a few key modifications to the YOLOv5 and optimize it for face detection. These modifications include adding a five-point landmark regression head, using a stem block at the input of the backbone, using smaller-size kernels in the SPP, and adding a P6 output in the PAN block. We design detectors of different model sizes, from an extra-large model to achieve the best performance to a super small model for real-time detection on an embedded or mobile device. Experiment results on the WiderFace dataset show that on VGA images, our face detectors can achieve state-of-the-art performance in almost all the Easy, Medium, and Hard subsets, exceeding the more complex designated face detectors. The code is available at \url{https://github.com/deepcam-cn/yolov5-face}