FDLite: A Single Stage Lightweight Face Detector Network

TL;DR

FDLite is a lightweight face detection network designed with a custom backbone and trained using standard loss functions, achieving high accuracy with significantly fewer parameters and FLOPs.

Contribution

This work introduces a novel lightweight backbone and a simplified training approach for face detection, maintaining high accuracy with minimal computational resources.

Findings

Achieves 92.3% AP on easy subset of WIDER FACE

Uses only standard loss functions and training strategies

Has 0.26M parameters and 0.94 GFLOPs

Abstract

Face detection is frequently attempted by using heavy pre-trained backbone networks like ResNet-50/101/152 and VGG16/19. Few recent works have also proposed lightweight detectors with customized backbones, novel loss functions and efficient training strategies. The novelty of this work lies in the design of a lightweight detector while training with only the commonly used loss functions and learning strategies. The proposed face detector grossly follows the established RetinaFace architecture. The first contribution of this work is the design of a customized lightweight backbone network (BLite) having 0.167M parameters with 0.52 GFLOPs. The second contribution is the use of two independent multi-task losses. The proposed lightweight face detector (FDLite) has 0.26M parameters with 0.94 GFLOPs. The network is trained on the WIDER FACE dataset. FDLite is observed to achieve 92.3\%, 89.8\%, and 82.2\% Average Precision (AP) on the easy, medium, and hard subsets of the WIDER FACE validation dataset, respectively.