Improved Selective Refinement Network for Face Detection
arXiv:1901.06651
Abstract
As a long-standing problem in computer vision, face detection has attracted much attention in recent decades for its practical applications. With the availability of face detection benchmark WIDER FACE dataset, much of the progresses have been made by various algorithms in recent years. Among them, the Selective Refinement Network (SRN) face detector introduces the two-step classification and regression operations selectively into an anchor-based face detector to reduce false positives and improve location accuracy simultaneously. Moreover, it designs a receptive field enhancement block to provide more diverse receptive field. In this report, to further improve the performance of SRN, we exploit some existing techniques via extensive experiments, including new data augmentation strategy, improved backbone network, MS COCO pretraining, decoupled classification module, segmentation branch and Squeeze-and-Excitation block. Some of these techniques bring performance improvements, while few of them do not well adapt to our baseline. As a consequence, we present an improved SRN face detector by combining these useful techniques together and obtain the best performance on widely used face detection benchmark WIDER FACE dataset.
Technical report, 8 pages, 6 figures
References in corpus (14)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Face Attention Network: An Effective Face Detector for the Occluded Faces
- Face Detection through Scale-Friendly Deep Convolutional Networks
- Rethinking ImageNet Pre-training
- Detecting Faces Using Region-based Fully Convolutional Networks
- Face Detection Using Improved Faster RCNN
- PyramidBox: A Context-assisted Single Shot Face Detector
- Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
- Feature Agglomeration Networks for Single Stage Face Detection
- Robust and High Performance Face Detector
- ScratchDet: Training Single-Shot Object Detectors from Scratch
- FA-RPN: Floating Region Proposals for Face Detection
Cited by in corpus (11)
- RetinaFace: Single-stage Dense Face Localisation in the Wild
- TinaFace: Strong but Simple Baseline for Face Detection
- Going Deeper Into Face Detection: A Survey
- LFFD: A Light and Fast Face Detector for Edge Devices
- EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
- Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
- Accurate Face Detection for High Performance
- RefineFace: Refinement Neural Network for High Performance Face Detection
- CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing
- Face Detection with Feature Pyramids and Landmarks
- Visual Diver Face Recognition for Underwater Human-Robot Interaction