期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
基于改进Faster RCNN的多尺度人脸检测网络研究 被引量:8
1
作者 宋梦媛 《自动化仪表》 CAS 2022年第11期39-43,48,共6页
针对人脸检测场景趋于多样化和复杂化的特点,考虑到大量遮挡、低分辨率和失真引起的人脸检测困难问题,提出了一种基于改进快速区域卷积神经网络(FasterRCNN)的多尺度人脸检测网络。首先,基于数据增强产生大量样本,从而提高数据多样性。... 针对人脸检测场景趋于多样化和复杂化的特点,考虑到大量遮挡、低分辨率和失真引起的人脸检测困难问题,提出了一种基于改进快速区域卷积神经网络(FasterRCNN)的多尺度人脸检测网络。首先,基于数据增强产生大量样本,从而提高数据多样性。其次,基于视觉几何组(VGG-16)网络微调预训练模型,生成大量难负例挖掘(HNM)样本并执行多尺度再训练,从而提高模型鲁棒性。最后,将生成的检测边界框转换为椭圆,从而更紧密包围人脸区域。在试验环节,基于预先训练的VGG-16模型在HNM样本上进行训练与测试,确定最佳数据增强组合。所提网络识别准确率为93.38%,召回率为89.52%,F分数为91.65%。所提多尺度人脸检测网络可以有效应用于大量遮挡、低分辨率和失真图像,为小样本人脸检测发展提供了一定参考。 展开更多
关键词 智慧校园 人脸检测 数据增强 难负例挖掘 深度卷积神经网络
下载PDF
CasNet:A Cascade Coarse-to-Fine Network for Semantic Segmentation 被引量:2
2
作者 Zhenyang Wang Zhidong Deng Shiyao Wang 《Tsinghua Science and Technology》 SCIE EI CAS CSCD 2019年第2期207-215,共9页
Semantic segmentation is a fundamental topic in computer vision. Since it is required to make dense predictions for an entire image, a network can hardly achieve good performance on various kinds of scenes. In this pa... Semantic segmentation is a fundamental topic in computer vision. Since it is required to make dense predictions for an entire image, a network can hardly achieve good performance on various kinds of scenes. In this paper, we propose a cascade coarse-to-fine network called CasNet, which focuses on regions that are difficult to make pixel-level labels. The CasNet comprises three branches. The first branch is designed to produce coarse predictions for easy-to-label pixel regions. The second one learns to distinguish the relatively difficult-to-label pixels from the entire image. Finally, the last branch generates final predictions by combining both the coarse and the fine prediction results through a weighting coefficient that is estimated by the second branch. Three branches focus on their own objectives and collaboratively learn to predict from coarse-to-fine predictions. To evaluate the performance of the proposed network, we conduct experiments on two public datasets: SIFT Flow and Stanford Background. We show that these three branches can be trained in an end-to-end manner, and the experimental results demonstrate that the proposed CasNet outperforms existing state-of-the-art models, and it achieves prediction accuracy of 91.6% and 89.7% on SIFT Flow and Standford Background, respectively. 展开更多
关键词 SEMANTIC SEGMENTATION convolutional neural NETWORK hard negative mining
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部