Papers
arxiv:1708.03979

SSH: Single Stage Headless Face Detector

Published on Aug 14, 2017
Authors:
,
,
,

Abstract

A single-stage headless face detector, SSH, achieves state-of-the-art performance without using a head or image pyramid, and is faster and lighter than existing methods.

AI-generated summary

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 https://github.com/mahyarnajibi/SSH.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1708.03979 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/1708.03979 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1708.03979 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.