عنوان انگلیسی مقاله:
Hyperspectral imagery classification with deep metric learning
ترجمه فارسی عنوان مقاله:
طبقه بندی تصاویر ابر طیفی با یادگیری متریک عمیق
Sciencedirect - Elsevier - Neurocomputing, 356 (2019) 217-227: doi:10:1016/j:neucom:2019:05:019
Xianghai Cao ∗, Yiming Ge , Renjie Li , Jing Zhao , Licheng Jiao
The high dimensionality of hyperspectral imagery often introduces challenge for the conventional data analysis techniques. In order to improve the classification performance of hyperspectral imagery, metric learning is often introduced to assign small distances between samples from the same class and large dis- tances from different class. However, most of the traditional metric learning methods only adopt linear transformations, which cannot capture the complex nonlinear relationships between high dimensional samples. Inspired by the successful application of deep learning for the classification of hyperspectral imagery. In this paper, the deep neural network is introduced to learn the discriminating metric for the classification of hyperspectral images. In order to improve the reliability of classification results, the spec- tral and spatial information are combined with weighted classification probabilities. Experimental results demonstrate that the proposed method achieves satisfactory classification performance when compared with other metric learning methods or deep models.
Keywords: Deep metric learning | Hyperspectral imagery | Feature fusion | Classification