TinaFace: Strong but Simple Baseline for Face Detection

TL;DR

TinaFace introduces a simple yet effective face detection baseline using generic object detection modules, achieving state-of-the-art results on the challenging WIDER FACE benchmark with a ResNet-50 backbone.

Contribution

The paper demonstrates that a straightforward approach based on existing generic object detection modules can achieve competitive face detection performance, simplifying the design process.

Findings

TinaFace achieves 92.1% AP on WIDER FACE test set with single model and scale.

Using test time augmentation improves AP to 92.4%.

The method surpasses many recent face detectors with larger backbones.

Abstract

Face detection has received intensive attention in recent years. Many works present lots of special methods for face detection from different perspectives like model architecture, data augmentation, label assignment and etc., which make the overall algorithm and system become more and more complex. In this paper, we point out that \textbf{there is no gap between face detection and generic object detection}. Then we provide a strong but simple baseline method to deal with face detection named TinaFace. We use ResNet-50 \cite{he2016deep} as backbone, and all modules and techniques in TinaFace are constructed on existing modules, easily implemented and based on generic object detection. On the hard test set of the most popular and challenging face detection benchmark WIDER FACE \cite{yang2016wider}, with single-model and single-scale, our TinaFace achieves 92.1\% average precision (AP), which exceeds most of the recent face detectors with larger backbone. And after using test time augmentation (TTA), our TinaFace outperforms the current state-of-the-art method and achieves 92.4\% AP. The code will be available at \url{https://github.com/Media-Smart/vedadet}.