Weakly supervised multiscale-inception learning for web-scale face recognition
文献类型：会议论文
| 作者 | Cheng, Cheng1; Xing, Junliang2; Feng, Youji1; Liu, Pengcheng1 ; Shao, Xiaohu1; Li, Kai2; Zhou, Xiang-Dong1
|
| 出版日期 | 2018 |
| 会议日期 | September 17, 2017 - September 20, 2017 |
| 会议地点 | Beijing, China |
| DOI | 10.1109/ICIP.2017.8296394 |
| 页码 | 815-819 |
| 英文摘要 | Supervised deep learning models like convolutional neural network (CNN) have shown very promising results for the face recognition problem, which often require a huge number of labeled face images. Since manually labeling a large training set is a very difficult and time-consuming task, it is very beneficial if the deep model can be trained from face samples with only weak annotations. In this paper, we propose a general framework to train a deep CNN model with weakly labeled facial images that are available on the Internet. Specifically, we first design a deep Multiscale-Inception CNN (MICNN) architecture to exploit the multi-scale information for face recognition. Then, we train an initial MICNN model with only a limited number of labeled samples. After that, we propose a dual-level sample selection strategy to further fine-tune the MICNN model with the weakly labeled samples from both the sample level and class level, which aims to skip outliers and select more samples from confusing class pairs during training. Extensive experimental results on the LFW and YTF benchmarks demonstrate the effectiveness of the proposed method. © 2017 IEEE. |
| 会议录 | 24th IEEE International Conference on Image Processing, ICIP 2017
 |
| 语种 | 英语 |
| ISSN号 | 15224880 |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/7974]  |
| 专题 | 智能安全技术研究中心 |
| 作者单位 | 1.Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, China; 2.Institute of Automation, Chinese Academy of Sciences, China |
| 推荐引用方式 GB/T 7714 | Cheng, Cheng,Xing, Junliang,Feng, Youji,et al. Weakly supervised multiscale-inception learning for web-scale face recognition[C]. 见:. Beijing, China. September 17, 2017 - September 20, 2017. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。