Institutional Repository of Chinese Acad Sci, Inst Solid State Phys, Hefei 230031, Anhui, Peoples R China
Procedural Learning With Robust Visual Features via Low Rank Prior | |
Li, Haifeng1,2; Chen, Li1; Ding, Hailun3; Li, Qi4; Sun, Bingyu5![]() | |
2019 | |
发表期刊 | IEEE ACCESS
![]() |
ISSN | 2169-3536 |
摘要 | In order to apply a convolutional neural network (CNN) to unseen datasets, a common way is to train a CNN using a pre-trained model on a big dataset by fine-tuning it instead of starting from scratch. How to control the fine-tuning progress to get the desired properties is still a challenging problem. Our key observation is that the visual features of the pre-trained model have rich information and can be explored during the training process. A natural thought is to employ these features and design a control strategy to improve the performance of the transfer learning process. In this paper, a procedural learning framework using the learned low-rank component of the visual features both in the pre-trained model and the training process is proposed to improve the accuracy and generalizability of the CNN. In this framework, we presented an approach to yield independent visualization features (IVFs). We found via robust independent component analysis that the low-rank components of IVFs provided robust features for our framework. Then, we design a Wasserstein regularization to control the transportation of the distribution of IVFs from a pre-trained model to a final model via the Wasserstein distance. The experiments on the Cifar-10 and Cifar-100 datasets via a VGG-style CNN model showed that our method effectively improves the classification results and convergence speed. The basic idea is that exploring visual features can also potentially inspire other topics, such as image detection and reinforcement learning. |
关键词 | Low-rank approximation procedural learning knowledge transfer robustness visual feature sparse |
DOI | 10.1109/ACCESS.2019.2894841 |
关键词[WOS] | ALGORITHM |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Science Foundation of China[41571397] ; National Science Foundation of China[41501442] ; National Science Foundation of China[51778242] ; National Science Foundation of China[61773360] ; National Science Foundation of China[41871364] ; Natural Science Foundation of Hunan Province[2016JJ3144] ; Natural Science Foundation of Hunan Province[2016JJ2006] |
项目资助者 | National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; National Science Foundation of China ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province ; Natural Science Foundation of Hunan Province |
WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
WOS类目 | Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications |
WOS记录号 | WOS:000459612400001 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.hfcas.ac.cn:8080/handle/334002/42151 |
专题 | 中科院固体物理研究所 |
通讯作者 | Wu, Guohua |
作者单位 | 1.Cent S Univ, Sch Geosci & Infophys, Changsha, Hunan, Peoples R China 2.Henan Lab Spatial Informat Applicat Ecol Environm, Zhengzhou, Henan, Peoples R China 3.Cent S Univ, Sch Software, Changsha, Hunan, Peoples R China 4.Cent S Univ, Sch Informat Sci & Engn, Changsha, Hunan, Peoples R China 5.Chinese Acad Sci, Inst Intelligent Machine, Hefei, Anhui, Peoples R China 6.Cent S Univ, Sch Traff & Transportat Engn, Changsha, Hunan, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Haifeng,Chen, Li,Ding, Hailun,et al. Procedural Learning With Robust Visual Features via Low Rank Prior[J]. IEEE ACCESS,2019,7(无):18884-18893. |
APA | Li, Haifeng,Chen, Li,Ding, Hailun,Li, Qi,Sun, Bingyu,&Wu, Guohua.(2019).Procedural Learning With Robust Visual Features via Low Rank Prior.IEEE ACCESS,7(无),18884-18893. |
MLA | Li, Haifeng,et al."Procedural Learning With Robust Visual Features via Low Rank Prior".IEEE ACCESS 7.无(2019):18884-18893. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Procedural Learning (13747KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论