LFFD: A Light and Fast Face Detector for Edge Devices

Abstract

Face detection, as a fundamental technology for various applications, is always deployed on edge devices which have limited memory storage and low computing power. This paper introduces a Light and Fast Face Detector (LFFD) for edge devices. The proposed method is anchor-free and belongs to the one-stage category. Specifically, we rethink the importance of receptive field (RF) and effective receptive field (ERF) in the background of face detection. Essentially, the RFs of neurons in a certain layer are distributed regularly in the input image and theses RFs are natural "anchors". Combining RF "anchors" and appropriate RF strides, the proposed method can detect a large range of continuous face scales with 100% coverage in theory. The insightful understanding of relations between ERF and face scales motivates an efficient backbone for one-stage detection. The backbone is characterized by eight detection branches and common layers, resulting in efficient computation. Comprehensive and extensive experiments on popular benchmarks: WIDER FACE and FDDB are conducted. A new evaluation schema is proposed for application-oriented scenarios. Under the new schema, the proposed method can achieve superior accuracy (WIDER FACE Val/Test -- Easy: 0.910/0.896, Medium: 0.881/0.865, Hard: 0.780/0.770; FDDB -- discontinuous: 0.973, continuous: 0.724). Multiple hardware platforms are introduced to evaluate the running efficiency. The proposed method can obtain fast inference speed (NVIDIA TITAN Xp: 131.45 FPS at 640x480; NVIDIA TX2: 136.99 PFS at 160x120; Raspberry Pi 3 Model B+: 8.44 FPS at 160x120) with model size of 9 MB.

arXiv comment10 pages, 4 figures

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Pruning Convolutional Neural Networks for Resource Efficient Inference
• Deep Face Recognition: A Survey
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• Some Improvements on Deep Convolutional Neural Network Based Image Classification
• Improved Selective Refinement Network for Face Detection
• Selective Refinement Network for High Performance Face Detection
• Robust and High Performance Face Detector
• Face R-CNN

Cited by in corpus (7)

• Tiny Machine Learning: Progress and Futures
• Detect Faces Efficiently: A Survey and Evaluations
• Going Deeper Into Face Detection: A Survey
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
• RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
• CenterFace: Joint Face Detection and Alignment Using Face as Point
• MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation