高光谱成像
计算机科学
稳健性(进化)
人工智能
残余物
噪音(视频)
频道(广播)
模式识别(心理学)
对偶(语法数字)
噪声数据
图像(数学)
数据挖掘
算法
文学类
化学
艺术
基因
生物化学
计算机网络
作者
Yimin Xu,Zhaokui Li,Wei Li,Qian Du,Cuiwei Liu,Zhuoqun Fang,Lin Zhai
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2021-03-08
卷期号:60: 1-11
被引量:53
标识
DOI:10.1109/tgrs.2021.3057689
摘要
Hyperspectral image (HSI) classification has drawn increasing attention recently. However, it suffers from noisy labels that may occur during field surveys due to a lack of prior information or human mistakes. To address this issue, this article proposes a novel dual-channel residual network (DCRN) to resolve HSI classification with noisy labels. Currently, the influence of noisy labels is reduced by simply detecting and removing those anomalous samples. Different from such a specifically designed noise cleansing method, DCRN is easy to implement but highly effective. It enhances its model robustness to noisy labels to a great extent by employing a novel dual-channel structure and a noise-robust loss function. In this way, DCRN can mitigate influence from noisy labels while fully utilizing useful information from mislabeled samples for augmented training. Experiments are conducted on several hyperspectral data sets with manually generated noisy labels to demonstrate its excellent performance. The code is available at https://github.com/Li-ZK/DCRN-2021 .
科研通智能强力驱动
Strongly Powered by AbleSci AI