Journal
2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019)
Volume -, Issue -, Pages 1108-1111Publisher
IEEE
DOI: 10.1109/igarss.2019.8898515
Keywords
Hyperspectral image classification; domain adaptation; transfer learning
Categories
Funding
- National Natural Science Foundation of China [61671307]
- Guangdong Special Support Program of Top-notch Young Professionals [2015TQ01X238]
- Shenzhen Scientific Research and Development Funding Program [JCYJ20180305124802421]
Ask authors/readers for more resources
Hyperspectral images (HSIs) has practical applications in many fields. In practical scenarios, machine learning often fails to handle changes between training (source) and testing (target) input distributions due to domain shifts. A big challenge in hyperspectral image classification is the small size of labeled data for classifier learning. We always face the situation that an HSI scene is not labeled all or with very limited number of labeled pixels, but we have sufficient labeled pixels in another HSI scene with similar land cover classes. In this paper, we propose a simple and effective method for domain adaptation called statistical fusion to minimize domain shifts by aligning the second-order and fourth-order statistics of source and target distributions. After two hyperspectral scenes are transformed into the similar property-space, any traditional HSI classification approaches can be used, and experimental results have validated the generalization of the proposed method.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available