S${}^3$FD: Single Shot Scale-invariant Face Detector

Abstract

This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S${}^3$FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces. Specifically, we try to solve the common problem that anchor-based detectors deteriorate dramatically as the objects become smaller. We make contributions in the following three aspects: 1) proposing a scale-equitable face detection framework to handle different scales of faces well. We tile anchors on a wide range of layers to ensure that all scales of faces have enough features for detection. Besides, we design anchor scales based on the effective receptive field and a proposed equal proportion interval principle; 2) improving the recall rate of small faces by a scale compensation anchor matching strategy; 3) reducing the false positive rate of small faces via a max-out background label. As a consequence, our method achieves state-of-the-art detection performance on all the common face detection benchmarks, including the AFW, PASCAL face, FDDB and WIDER FACE datasets, and can run at 36 FPS on a Nvidia Titan X (Pascal) for VGA-resolution images.

Accepted by ICCV 2017 + its supplementary materials; Updated the latest results on WIDER FACE

References in corpus (17)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• ParseNet: Looking Wider to See Better
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• Rethinking the Inception Architecture for Computer Vision
• A Fast and Accurate Unconstrained Face Detector
• Speed/accuracy trade-offs for modern convolutional object detectors
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• Occlusion Coherence: Detecting and Localizing Occluded Faces
• WIDER FACE: A Face Detection Benchmark
• Bootstrapping Face Detection with Hard Negative Examples
• Scalable Object Detection using Deep Neural Networks
• Face Detection with the Faster R-CNN

Cited by in corpus (10)

• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis
• Face Recognition in Low Quality Images: A Survey
• Face Detection in the Operating Room: Comparison of State-of-the-art Methods and a Self-supervised Approach
• Unsupervised Hard Example Mining from Videos for Improved Object Detection
• Wildest Faces: Face Detection and Recognition in Violent Settings
• Face Recognition in Unconstrained Conditions: A Systematic Review
• A Fast and Accurate System for Face Detection, Identification, and Verification
• Improving Face Detection Performance with 3D-Rendered Synthetic Data
• Survey of Face Detection on Low-quality Images