Face Detection through Scale-Friendly Deep Convolutional Networks

Abstract

In this paper, we share our experience in designing a convolutional network-based face detector that could handle faces of an extremely wide range of scales. We show that faces with different scales can be modeled through a specialized set of deep convolutional networks with different structures. These detectors can be seamlessly integrated into a single unified network that can be trained end-to-end. In contrast to existing deep models that are designed for wide scale range, our network does not require an image pyramid input and the model is of modest complexity. Our network, dubbed ScaleFace, achieves promising performance on WIDER FACE and FDDB datasets with practical runtime speed. Specifically, our method achieves 76.4 average precision on the challenging WIDER FACE dataset and 96% recall rate on the FDDB dataset with 7 frames per second (fps) for 900 * 1300 input image.

12 pages, 10 figures

References in corpus (7)

• Deep Residual Learning for Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Rich feature hierarchies for accurate object detection and semantic segmentation
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• Face Detection with the Faster R-CNN
• Grid Loss: Detecting Occluded Faces
• Faceness-Net: Face Detection through Deep Facial Part Responses

Cited by in corpus (30)

• Object Detection in 20 Years: A Survey
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• TinaFace: Strong but Simple Baseline for Face Detection
• Going Deeper Into Face Detection: A Survey
• Anchor Cascade for Efficient Face Detection
• EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
• FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
• Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
• Improved Selective Refinement Network for Face Detection
• Feature Agglomeration Networks for Single Stage Face Detection
• Deep Learning For Face Recognition: A Critical Analysis
• Accurate Face Detection for High Performance
• Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations
• RefineFace: Refinement Neural Network for High Performance Face Detection
• SFace: An Efficient Network for Face Detection in Large Scale Variations
• Seeing Small Faces from Robust Anchor's Perspective
• Segmentation is All You Need
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Wildest Faces: Face Detection and Recognition in Violent Settings
• Robust Face Detection via Learning Small Faces on Hard Images
• Adversarial Occlusion-aware Face Detection
• Faceness-Net: Face Detection through Deep Facial Part Responses
• Face Recognition in Unconstrained Conditions: A Systematic Review
• Improving Face Detection Performance with 3D-Rendered Synthetic Data
• A Fast and Accurate System for Face Detection, Identification, and Verification
• Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecture
• Survey of Face Detection on Low-quality Images
• KPNet: Towards Minimal Face Detector
• FHEDN: A based on context modeling Feature Hierarchy Encoder-Decoder Network for face detection