From Facial Parts Responses to Face Detection: A Deep Learning Approach

Abstract

In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99% on the challenging FDDB benchmark, outperforming the state-of-the-art method by a large margin of 2.91%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variation, which are the main difficulty and bottleneck of most existing face detection approaches. We show that despite the use of DCN, our network can achieve practical runtime speed.

To appear in ICCV 2015

References in corpus (2)

• Distilling the Knowledge in a Neural Network
• Speeding up Convolutional Neural Networks with Low Rank Expansions

Cited by in corpus (54)

• Improving Person Re-identification by Attribute and Identity Learning
• Residual Attention Network for Image Classification
• Multimodal Generative Models for Scalable Weakly-Supervised Learning
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Face Detection through Scale-Friendly Deep Convolutional Networks
• Object Detection with Deep Learning: A Review
• Look, Listen and Learn - A Multimodal LSTM for Speaker Identification
• PyramidBox: A Context-assisted Single Shot Face Detector
• FaceBoxes: A CPU Real-time Face Detector with High Accuracy
• S${}^3$FD: Single Shot Scale-invariant Face Detector
• Pilot Comparative Study of Different Deep Features for Palmprint Identification in Low-Quality Images
• Scale-Aware Face Detection
• Look at Boundary: A Boundary-Aware Face Alignment Algorithm
• Feature Agglomeration Networks for Single Stage Face Detection
• Selective Refinement Network for High Performance Face Detection
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• SFA: Small Faces Attention Face Detector
• Compact Convolutional Neural Network Cascade for Face Detection
• SFace: An Efficient Network for Face Detection in Large Scale Variations
• Identifying Bias in AI using Simulation
• Seeing Small Faces from Robust Anchor's Perspective
• From Facial Expression Recognition to Interpersonal Relation Prediction
• Grid Loss: Detecting Occluded Faces
• A Jointly Learned Deep Architecture for Facial Attribute Analysis and Face Detection in the Wild
• Unsupervised Hard Example Mining from Videos for Improved Object Detection
• Generative Adversarial Networks with Decoder-Encoder Output Noise
• Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification
• Wildest Faces: Face Detection and Recognition in Violent Settings
• Robust Face Detection via Learning Small Faces on Hard Images
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• Revisit Lmser and its further development based on convolutional layers
• Joint Face Detection and Facial Motion Retargeting for Multiple Faces
• Faceness-Net: Face Detection through Deep Facial Part Responses
• Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
• Adversarial Occlusion-aware Face Detection
• Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
• To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection
• Image-Hashing-Based Anomaly Detection for Privacy-Preserving Online Proctoring
• Multi-Branch Fully Convolutional Network for Face Detection
• A Fast and Accurate System for Face Detection, Identification, and Verification
• Beyond Context: Exploring Semantic Similarity for Tiny Face Detection
• What can we learn about CNNs from a large scale controlled object dataset?
• Face Detection with End-to-End Integration of a ConvNet and a 3D Model
• Improved Face Detection and Alignment using Cascade Deep Convolutional Network
• Objects as context for detecting their semantic parts
• FA-RPN: Floating Region Proposals for Face Detection
• Precise Box Score: Extract More Information from Datasets to Improve the Performance of Face Detection
• Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained "Hard Faces"
• KPNet: Towards Minimal Face Detector
• Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors
• Face Detection in Repeated Settings
• Object Specific Deep Learning Feature and Its Application to Face Detection
• Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks
• PoET-BiN: Power Efficient Tiny Binary Neurons