文章名：Supervised Deep Feature Extraction for Hyperspectral Image Classification
- 期刊名: IEEE Transactions on Geoscience & Remote Sensing
- 摘要：提出了一种基于siamese网络（S-CNN）的改进监督深度特征提取方法。首先，利用5层cnn对高光谱数据提取深层特征（cnn被当做一种非线性转换函数）；接着，训练由两个cnn组成的siamese网络学习类内之间的低易变性以及类间的高易变性。特别地，S-CNN的训练loss是margin ranking loss function（能够提取区分性更强（more discriminative）的分类特征）。最终在三个数据集上提取特征输入到SVM中，实现比传统方法更好的分类效果。
-
网络结构
bing5-2769673-small.gif -
S-CNN的loss
CodeCogsEqn.gif
CodeCogsEqn.gif
p1和 p2是输入图像对，f（p1）和f（p2）是CNN提取的特征，D（）代表欧氏距离。 - 相关工作
1 .J. Bromley, I. Guyon, Y. LeCun, E. Säckinger, and R. Shah, “Signature verification using a ‘Siamese’ time delay neural network,” in Proc. Adv. Neural Inf. Process. Syst., 1994, pp. 737–744.
2 X. Han, T. Leung, Y. Jia, R. Sukthankar, and A. C. Berg, “MatchNet: Unifying feature and metric learning for patch-based matching,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 3279–3286.
3 A. Dosovitskiy, J. T. Springenberg, M. Riedmiller, and T. Brox, “Discriminative unsupervised feature learning with convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 766–774.
参考文献：
Liu B, Yu X, Zhang P, et al. Supervised Deep Feature Extraction for Hyperspectral Image Classification[J]. IEEE Transactions on Geoscience & Remote Sensing, 2018, 56(4):1909-1921.
