DeepAI AI Chat
Log In Sign Up

SSH: Single Stage Headless Face Detector

by   Mahyar Najibi, et al.
University of Maryland

We introduce the Single Stage Headless (SSH) face detector. Unlike two stage proposal-classification detectors, SSH detects faces in a single stage directly from the early convolutional layers in a classification network. SSH is headless. That is, it is able to achieve state-of-the-art results while removing the "head" of its underlying classification network -- i.e. all fully connected layers in the VGG-16 which contains a large number of parameters. Additionally, instead of relying on an image pyramid to detect faces with various scales, SSH is scale-invariant by design. We simultaneously detect faces with different scales in a single forward pass of the network, but from different layers. These properties make SSH fast and light-weight. Surprisingly, with a headless VGG-16, SSH beats the ResNet-101-based state-of-the-art on the WIDER dataset. Even though, unlike the current state-of-the-art, SSH does not use an image pyramid and is 5X faster. Moreover, if an image pyramid is deployed, our light-weight network achieves state-of-the-art on all subsets of the WIDER dataset, improving the AP by 2.5 SSH also reaches state-of-the-art results on the FDDB and Pascal-Faces datasets while using a small input size, leading to a runtime of 50 ms/image on a GPU. The code is available at


page 1

page 8


Face Detection through Scale-Friendly Deep Convolutional Networks

In this paper, we share our experience in designing a convolutional netw...

Online PCB Defect Detector On A New PCB Defect Dataset

Previous works for PCB defect detection based on image difference and im...

Finding Tiny Faces

Though tremendous strides have been made in object recognition, one of t...

Revisiting a single-stage method for face detection

Although accurate, two-stage face detectors usually require more inferen...

Light-Head R-CNN: In Defense of Two-Stage Object Detector

In this paper, we first investigate why typical two-stage methods are no...

ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch

Current state-of-the-art object objectors are fine-tuned from the off-th...

RetinaFace: Single-stage Dense Face Localisation in the Wild

Though tremendous strides have been made in uncontrolled face detection,...

Code Repositories


SSH Face Detector in Keras

view repo