FDLite: A Single Stage Lightweight Face Detector Network
This work addresses the problem of efficient face detection for resource-constrained applications, but it is incremental as it builds on the established RetinaFace architecture.
The paper tackles face detection by proposing FDLite, a lightweight single-stage detector with 0.26M parameters and 0.94 GFLOPs, achieving 92.3%, 89.8%, and 82.2% AP on the easy, medium, and hard subsets of the WIDER FACE validation dataset.
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.