LFFD: A Light and Fast Face Detector for Edge Devices

Code

• github.com/YonghaoHe/A-Light-and-Fast-Face-Detector-for-Edge-Devices
  OfficialIn papermxnet★ 0
• github.com/osmr/imgclsmob
  mxnet★ 3,015
• github.com/YonghaoHe/LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices
  mxnet★ 0
• github.com/aoru45/BasketNet
  pytorch★ 0
• github.com/donnyyou/pytorch-lffd
  mxnet★ 0
• github.com/jacke121/A-Light-and-Fast-Face-Detector-for-Edge-Devices
  tf★ 0
• github.com/Qengineering/LFFD-ncnn-Raspberry-Pi-4
  none★ 0
• github.com/borhanMorphy/light-face-detection
  pytorch★ 0
• github.com/gouthamvgk/facemesh_coreml_tf
  tf★ 0
• github.com/borhanMorphy/fastface
  pytorch★ 0

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.

Tasks

Benchmark Results

Reproductions