1. Joint learning of deep multi-scale features and diversified metrics for hyperspectral image classification
- Author
-
Jiaxin Shan, Zhiqiang Gong, Yang Yu, Ping Zhong, and Weidong Hu
- Subjects
Similarity (geometry) ,Contextual image classification ,business.industry ,Computer science ,Deep learning ,Feature extraction ,0211 other engineering and technologies ,Hyperspectral imaging ,Pattern recognition ,02 engineering and technology ,Support vector machine ,Discriminative model ,Metric (mathematics) ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,021101 geological & geomatics engineering - Abstract
Due to the high spectral resolution and the similarity of some spectrums between different classes, hyperspectral image classification turns out to be an important but challenging task. Researches show the powerful ability of deep learning for hyperspectral image classification. However, the lack of training samples makes it difficult to extract discriminative features and achieve performance as expected. To solve the problem, a multi-scale CNN which can extract multi-scale features is designed for hyperspectral image classification. Furthermore, D-DSML, a diversified metric, is proposed to further improve the representational ability of deep methods. In this paper, a D-DSML-MSCNN method, which jointly learns deep multi-scale features and diversified metrics for hyperspectral image classification, is proposed to take both advantages of D-DSML and MSCNN. Experiments are conducted on Pavia University data to show the effectiveness of our method for hyperspectral image classification. The results show the advantage of our method when compared with other recent results.
- Published
- 2017