前戏
最近出了很多论文,各种SOTA。比如(点击可访问):
商汤等提出:统一多目标跟踪框架
亚马逊提出:用于人群计数的尺度感知注意力网络
今天po的改进SRN人脸检测算法(Improved Selective Refinement Network for Face Detection),其刚刚击败半个月前中星微提出的的VIM-FD算法,所以为目前人脸检测方向的SOTA论文。
正文
《Improved Selective Refinement Network for Face Detection》
arXiv: https://arxiv.org/abs/1901.06651
作者团队:中科院自动化所和京东 AI研究院
注:2019年01月23日刚出炉的paper
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.
摘要:近年来,人脸检测作为计算机视觉中长期存在的问题,因其实际应用而备受关注。随着人脸检测基准WIDER FACE数据集的推出,近年来各种算法已经取得了很多进展。其中,选择性细化网络(SRN)人脸检测器选择性地将两步分类和回归操作引入到基于 anchor的人脸检测器中,以同时减少误报并提高定位精度。此外,它设计了一个感受野增强模块,以提供更多样化的感受野。在本文中,为了进一步提高SRN的性能,我们通过广泛的实验开发了一些现有技术,包括新的数据增强策略,改进的骨干网络,MS COCO预训练,解耦分类模块,分段分支和Squeeze-Excitation块。其中一些技术可以带来性能改进,而其中很少一些技术不能很好地适应我们的基线。因此,我们通过将这些有用的技术结合在一起,提出了一种改进的SRN人脸检测器,并在广泛使用的人脸检测基准WIDER FACE数据集上获得了最佳性能。
Selective Refinement Network
Network structure illustration
The brief overview of Selective Refinement Network with segmentation branch
创新点
Selective Two-step Classification
Selective Two-step Regression
Receptive Field Enhancement
注:论文中还分享了一些改进的tricks,如data augmentation、feature extractor、training strategy
实验结果
想要了解最新最快最好的论文速递、开源项目和干货资料,欢迎加入CVer学术交流群。涉及图像分类、目标检测、图像分割、人脸检测&识别、目标跟踪、GANs、学术竞赛交流、Re-ID、风格迁移、医学影像分析、姿态估计、OCR、SLAM、场景文字检测&识别和超分辨率等方向。