Face Detection Using Improved Faster RCNN
arXiv:1802.02142
Abstract
Faster RCNN has achieved great success for generic object detection including PASCAL object detection and MS COCO object detection. In this report, we propose a detailed designed Faster RCNN method named FDNet1.0 for face detection. Several techniques were employed including multi-scale training, multi-scale testing, light-designed RCNN, some tricks for inference and a vote-based ensemble method. Our method achieves two 1th places and one 2nd place in three tasks over WIDER FACE validation dataset (easy set, medium set, hard set).
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- DSSD : Deconvolutional Single Shot Detector
- Face Attention Network: An Effective Face Detector for the Occluded Faces
- An Implementation of Faster RCNN with Study for Region Sampling
- Detecting Faces Using Region-based Fully Convolutional Networks
- Scale-Aware Face Detection
- Face R-CNN
Cited by in corpus (14)
- RetinaFace: Single-stage Dense Face Localisation in the Wild
- TinaFace: Strong but Simple Baseline for Face Detection
- Detect Faces Efficiently: A Survey and Evaluations
- Going Deeper Into Face Detection: A Survey
- EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
- Improved Selective Refinement Network for Face Detection
- Recent Advances in Deep Learning for Object Detection
- Accurate Face Detection for High Performance
- RefineFace: Refinement Neural Network for High Performance Face Detection
- CenterFace: Joint Face Detection and Alignment Using Face as Point
- ASFD: Automatic and Scalable Face Detector
- DSFD: Dual Shot Face Detector
- Robust Face Detection via Learning Small Faces on Hard Images
- Robust Human Identity Anonymization using Pose Estimation