# LFFD: A Light and Fast Face Detector for Edge Devices

arXiv: https://arxiv.org/abs/1904.10633 · HTML: https://mlsanity.com/paper/1904.10633/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2019.

## Built on by (most cited first, 21 of 21)

- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection](https://mlsanity.com/paper/2305.13625/) (2023)
- [Going Deeper Into Face Detection: A Survey](https://mlsanity.com/paper/2103.14983/) (2021)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [Detect Faces Efficiently: A Survey and Evaluations](https://mlsanity.com/paper/2112.01787/) (2021)
- [EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection](https://mlsanity.com/paper/2204.01209/) (2022)
- [YOLO-TS: Real-Time Traffic Sign Detection with Enhanced Accuracy Using Optimized Receptive Fields and Anchor-Free Fusion](https://mlsanity.com/paper/2410.17144/) (2024)
- [MinUn: Accurate ML Inference on Microcontrollers](https://mlsanity.com/paper/2210.16556/) (2022)
- [EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detection](https://mlsanity.com/paper/2302.11816/) (2023)
- [Attribute-Guided Encryption with Facial Texture Masking](https://mlsanity.com/paper/2305.13548/) (2023)
- [FDLite: A Single Stage Lightweight Face Detector Network](https://mlsanity.com/paper/2406.19107/) (2024)
- [MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation](https://mlsanity.com/paper/2110.10953/) (2021)
- [Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion](https://mlsanity.com/paper/2311.16613/) (2023)
- [RetriBooru: Leakage-Free Retrieval of Conditions from Reference Images for Subject-Driven Generation](https://mlsanity.com/paper/2312.02521/) (2023)
- [B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM Pruning](https://mlsanity.com/paper/2501.16917/) (2025)
- [EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection](https://mlsanity.com/paper/2306.02277/) (2023)
- [A Diver Attention Estimation Framework for Effective Underwater Human-Robot Interaction](https://mlsanity.com/paper/2209.14447/) (2022)
- [A Comparative Study of Face Detection Algorithms for Masked Face Detection](https://mlsanity.com/paper/2305.11077/) (2023)
- [FaceTouch: Detecting hand-to-face touch with supervised contrastive learning to assist in tracing infectious disease](https://mlsanity.com/paper/2308.12840/) (2023)

## Abstract (arXiv)

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.