Remote sensing image scene classification with noisy label distillation
文献类型：期刊论文
| 作者 | Zhang, Rui1,3; Chen, Zhenghao3; Zhang, Sanxing1,3; Song, Fei2,3; Zhang, Gang3; Zhou, Quancheng1,3; Lei, Tao3 |
| 刊名 | Remote Sensing
 |
| 出版日期 | 2020-08-01 |
| 卷号 | 12期号:15 |
| ISSN号 | 2072-4292 |
| 关键词 | scene classification teacher-student noisy labels knowledge distillation remote sensing images |
| DOI | 10.3390/RS12152376 |
| 文献子类 | 期刊论文 |
| 英文摘要 | The widespread applications of remote sensing image scene classification-based Convolutional Neural Networks (CNNs) are severely affected by the lack of large-scale datasets with clean annotations. Data crawled from the Internet or other sources allows for the most rapid expansion of existing datasets at a low-cost. However, directly training on such an expanded dataset can lead to network overfitting to noisy labels. Traditional methods typically divide this noisy dataset into multiple parts. Each part fine-tunes the network separately to improve performance further. These approaches are inefficient and sometimes even hurt performance. To address these problems, this study proposes a novel noisy label distillation method (NLD) based on the end-to-end teacher-student framework. First, unlike general knowledge distillation methods, NLD does not require pre-training on clean or noisy data. Second, NLD effectively distills knowledge from labels across a full range of noise levels for better performance. In addition, NLD can benefit from a fully clean dataset as a model distillation method to improve the student classifier's performance. NLD is evaluated on three remote sensing image datasets, including UC Merced Land-use, NWPU-RESISC45, AID, in which a variety of noise patterns and noise amounts are injected. Experimental results show that NLD outperforms widely used directly fine-tuning methods and remote sensing pseudo-labeling methods. © 2020 by the authors. |
| 出版地 | BASEL |
| WOS研究方向 | Remote Sensing |
| 语种 | 英语 |
| 出版者 | MDPI |
| WOS记录号 | WOS:000559016000001 |
| 源URL | [http://ir.ioe.ac.cn/handle/181551/10130]  |
| 专题 | 光电技术研究所_光电探测技术研究室（三室） |
| 作者单位 | 1.University of Chinese Academy of Sciences, Beijing; 100049, China; 2.School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu; 611731, China 3.Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu; 610209, China; |
| 推荐引用方式 GB/T 7714 | Zhang, Rui,Chen, Zhenghao,Zhang, Sanxing,et al. Remote sensing image scene classification with noisy label distillation[J]. Remote Sensing,2020,12(15). |
| APA | Zhang, Rui.,Chen, Zhenghao.,Zhang, Sanxing.,Song, Fei.,Zhang, Gang.,...&Lei, Tao.(2020).Remote sensing image scene classification with noisy label distillation.Remote Sensing,12(15). |
| MLA | Zhang, Rui,et al."Remote sensing image scene classification with noisy label distillation".Remote Sensing 12.15(2020). |
入库方式： OAI收割
来源：光电技术研究所
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。