Face Attention Network: An Effective Face Detector for the Occluded Faces

Abstract

The performance of face detection has been largely improved with the development of convolutional neural network. However, the occlusion issue due to mask and sunglasses, is still a challenging problem. The improvement on the recall of these occluded cases usually brings the risk of high false positives. In this paper, we present a novel face detector called Face Attention Network (FAN), which can significantly improve the recall of the face detection problem in the occluded case without compromising the speed. More specifically, we propose a new anchor-level attention, which will highlight the features from the face region. Integrated with our anchor assign strategy and data augmentation techniques, we obtain state-of-art results on public face detection benchmarks like WiderFace and MAFA. The code will be released for reproduction.

References in corpus (8)

• Focal Loss for Dense Object Detection
• Feature Pyramid Networks for Object Detection
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• Face Detection through Scale-Friendly Deep Convolutional Networks
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• Scale-Aware Face Detection
• Grid Loss: Detecting Occluded Faces
• Adversarial Occlusion-aware Face Detection

Cited by in corpus (37)

• A Survey of Deep Learning-based Object Detection
• Towards Large-Scale Small Object Detection: Survey and Benchmarks
• Object Detection in 20 Years: A Survey
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
• SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images
• TinaFace: Strong but Simple Baseline for Face Detection
• Face Detection Using Improved Faster RCNN
• EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
• A Survey on Masked Facial Detection Methods and Datasets for Fighting Against COVID-19
• Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
• Improved Selective Refinement Network for Face Detection
• WIDER Face and Pedestrian Challenge 2018: Methods and Results
• Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition
• Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
• iQIYI-VID: A Large Dataset for Multi-modal Person Identification
• Deep Learning For Face Recognition: A Critical Analysis
• Accurate Face Detection for High Performance
• Selective Refinement Network for High Performance Face Detection
• Robust and High Performance Face Detector
• A survey of face recognition techniques under occlusion
• RefineFace: Refinement Neural Network for High Performance Face Detection
• HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces
• Segmentation is All You Need
• Face Detection with Feature Pyramids and Landmarks
• DSFD: Dual Shot Face Detector
• Wildest Faces: Face Detection and Recognition in Violent Settings
• SMA-STN: Segmented Movement-Attending Spatiotemporal Network forMicro-Expression Recognition
• Robust Face Detection via Learning Small Faces on Hard Images
• Adversarial Occlusion-aware Face Detection
• Improving Face Detection Performance with 3D-Rendered Synthetic Data
• Face Recognition in Unconstrained Conditions: A Systematic Review
• Perceptual Image Super-Resolution with Progressive Adversarial Network
• Deep Imbalanced Attribute Classification using Visual Attention Aggregation
• On Improving the Generalization of Face Recognition in the Presence of Occlusions
• Non-contact Real time Eye Gaze Mapping System Based on Deep Convolutional Neural Network
• Selective Convolutional Network: An Efficient Object Detector with Ignoring Background