利用同质区特性的高光谱图像迁移学习分类

doi:10.3778/j.issn.1002-8331.2007-0080

摘要/Abstract

摘要：

深度卷积神经网络能充分利用特征间的内在联系，提高高光谱影像的可分性，近年来受到了广泛关注。但是，训练深度网络模型对大量标记样本的需求限制了此类方法的应用。将迁移学习思想引入遥感影像分类以减少对标记样本数量的需求。具体研究目标图像中每类只有一个标记样本的情况。通过对目标图像分割得到的同质区扩增目标域的训练样本数量，在此基础上运用深度孪生卷积神经网络减少源域图像与目标域图像的分布差异，实现对目标高光谱图像的最终分类。实验结果表明：同质区和孪生卷积网络的结合可提高半监督迁移学习分类的效果，较好地解决跨区域的高光谱图像分类问题。

关键词: 高光谱图像分类, 孪生神经网络, 图像分割, 同质区, 单样本学习, 半监督迁移学习

Abstract:

Deep convolutional neural networks can fully utilize the inner connections between features which improve the separability of the hyperspectral images and have been widely studied in recent years. However, the need for an abundant labeled sample for training deep network models limits the application of such methods. To cut the need for the number of labeled samples, the technology of transfer learning is adopted for remote sensing classification in this paper. The one-shot problem is concerned in which only a single sample of each class is available. Data augmentation is carried out, based on homogenous regions obtained by image segmentation. Using the deep Siamese CNN trained by augmentation samples, this paper can cut the divergence between the distributions of the source domain and target domain, and classify the target image. Experiment results based on cross-region hyperspectral image datasets show the effect of the combination of deep Siamese CNN and homogenous areas on semi-supervised transfer learning.

Key words: hyperspectral image classification, siamese neural network, image segmentation, homogeneous area, one-shot learning, semi-supervised transfer learning

周绍光，吴昊，赵婵娟，陈仁喜. 利用同质区特性的高光谱图像迁移学习分类[J]. 计算机工程与应用, 2021, 57(21): 224-233.

ZHOU Shaoguang, WU Hao, ZHAO Chanjuan, CHEN Renxi. Transfer Learning for Hyperspectral Image Classification Using Homogeneous Area Characteristics[J]. Computer Engineering and Applications, 2021, 57(21): 224-233.

参考文献

[1] LECUN Y，BOSER B，DENKER J S，et al.Backpropagation applied to handwritten zip code recognition[J].Neural Computation，1989，1（4）：541-551.
[2] JIAO L，LIANG M，CHEN H，et al.Deep fully convolutional network-based spatial distribution prediction for hyperspectral image classification[J].IEEE Transactions on Geoence and Remote Sensing，2017（10）：1-15.
[3] MEI S，JI J，HOU J，et al.Learning sensor-specific spatial-spectral features of hyperspectral images via convolutional neural networks[J].IEEE Transactions on Geoence & Remote Sensing，2017，55（8）：4520-4533.
[4] YANG J，ZHAO Y Q，CHAN J C.Learning and transferring deep joint spectral-spatial features for hyperspectral classification[J].IEEE Transactions on Geoscience and Remote Sensing，2017，55（8）：4729-4742.
[5] TUIA D，PERSELLO C，BRUZZONE L.Domain adaptation for the classification of remote sensing data：an overview of recent advances[J].IEEE Geoence & Remote Sensing Magazine，2016，4（2）：41-57.
[6] LI Z，TANG X，LI W，et al.A two-stage deep domain adaptation method for hyperspectral image classification[J].Remote Sensing，2020，12（7）：1054.
[7] MOTIIAN S，PICCIRLLI M，ADJEROH D A，et al.Unified deep supervised domain adaptation and generalization[C]//Proceedings of the IEEE International Conference on Computer Vision（ICCV），2017：5715-5725.
[8] FINK M.Object classification from a single example utilizing class relevance metrics[C]//Advances in Neural Information Processing Systems，2005：449-456.
[9] FEIFEI L，FERGUS R，PERONA P.One-shot learning of object categories[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2006，28（4）：594-611.
[10] KOCH G，ZEMEL R，SALAKHUTDINOV R.Siamese neural networks for one-shot image recognition[C]//ICML Deep Learning Workshop，2015.
[11] COMANICIU D，MEER P.Mean shift：a robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2002，24（5）：603-619.
[12] MICHAEL V D B，BOIX X，ROIG G，et al.SEEDS：superpixels extracted via energy-driven sampling[J].International Journal of Computer Vision，2015，111（3）：298-314.
[13] ACHANTA R，SHAJI A，SMITH K，et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2012.
[14] TARABALIKA Y，CHANUSSOT J，BENEDIKTSSON J A.Segmentation and classification of hyperspectral images using watershed transformation[J].Pattern Recognition，2010，43（7）：2367-2379.
[15] TUTZ D.Superpixel segmentation：an evaluation[C]//German Conference on Pattern Recognition，2015：555-562.
[16] DU Q，YANG H.Similarity-based unsupervised band selection for hyperspectral image analysis[J].IEEE Geoscience and Remote Sensing Letters，2008，5（4）：564-568.
[17] LIU M Y，TUZEL O，RAMALINGAM S，et al.Entropy rate superpixel Segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition，2011：2097-2104.
[18] NEUBERT P，PROTZEL P.Superpixel benchmark and comparison[C]//Proceedings of Forum Bildverarbeitung，2012：1-12.
[19] BROMLEY J，GUYON I，LECUN Y，et al.Signature verification using a “siamese” time delay neural network[C]//Advances in Neural Information Processing Systems，1994：737-744.
[20] HADSELL R，CHOPRA S，LECUN Y.Dimensionality reduction by learning an invariant mapping[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition（CVPR’06），2006：1735-1742.