判别式
计算机科学
人工智能
模式识别(心理学)
领域(数学分析)
嵌入
域适应
深度学习
源代码
上下文图像分类
机器学习
图像(数学)
分类器(UML)
数学
操作系统
数学分析
作者
Zhaokui Li,Ming Liu,Yushi Chen,Yimin Xu,Wei Li,Qian Du
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2021-02-19
卷期号:60: 1-18
被引量:168
标识
DOI:10.1109/tgrs.2021.3057066
摘要
One of the challenges in hyperspectral image (HSI) classification is that there are limited labeled samples to train a classifier for very high-dimensional data. In practical applications, we often encounter an HSI domain (called target domain) with very few labeled data, while another HSI domain (called source domain) may have enough labeled data. Classes between the two domains may not be the same. This article attempts to use source class data to help classify the target classes, including the same and new unseen classes. To address this classification paradigm, a meta-learning paradigm for few-shot learning (FSL) is usually adopted. However, existing FSL methods do not account for domain shift between source and target domain. To solve the FSL problem under domain shift, a novel deep cross-domain few-shot learning (DCFSL) method is proposed. For the first time, DCFSL tackles FSL and domain adaptation issues in a unified framework. Specifically, a conditional adversarial domain adaptation strategy is utilized to overcome domain shift, which can achieve domain distribution alignment. In addition, FSL is executed in source and target classes at the same time, which can not only discover transferable knowledge in the source classes but also learn a discriminative embedding model to the target classes. Experiments conducted on four public HSI data sets demonstrate that DCFSL outperforms the existing FSL methods and deep learning methods for HSI classification. Our source code is available at https://github.com/Li-ZK/DCFSL-2021 .
科研通智能强力驱动
Strongly Powered by AbleSci AI