Abstract
The classification of hyperspectral images (HSI) into categories that correlate to various land cover sorts such as water bodies, agriculture and urban areas, has gained significant attention in research due to its wide range of applications in fields, such as remote sensing, computer vision, and more. Supervised deep learning networks have demonstrated exceptional performance in HSI classification, capitalizing on their capacity for end-to-end optimization and leveraging their strong potential for nonlinear modeling. However, labelling HSIs, on the other hand, necessitates extensive domain knowledge and is a time-consuming and labour-intensive exercise. To address this issue, the proposed work introduces a novel semi-supervised network constructed with an autoencoder, Siamese action, and attention layers that achieves excellent classification accuracy with labelled limited samples. The proposed convolutional autoencoder is trained using the mass amount of unlabelled data to learn the refinement representation referred to as 3D-CAE. The added Siamese network improves the feature separability between different categories and attention layers improve classification by focusing on discriminative information and neglecting the unimportant bands. The efficacy of the proposed model’s performance was assessed by training and testing on both same-domain as well as cross-domain data and found to achieve 91.3 and 93.6 for Indian Pines and Salinas, respectively.
Similar content being viewed by others
Data availability
The hyperspectral datasets are open and available on https://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes
Code availability
The code used for the experiments in this research project is available upon request via mail.
References
Ranjan P, Girdhar A (2022) A comprehensive systematic review of deep learning methods for hyperspectral images classification. Int J Remote Sens 43(17):6221–6306
Sellami A, Farah M, Farah IR, Solaiman B (2019) Hyperspectral imagery classification based on semi-supervised 3-d deep neural network and adaptive band selection. Expert Syst Appl 129:246–259
Ball JE, Anderson DT, Chan CS (2017) Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community. J Appl Remote Sens 11(4):042609–042609
Nalepa J, Myller M, Imai Y, Honda K, Takeda T, Antoniak M (2020) Unsupervised segmentation of hyperspectral images using 3-d convolutional autoencoders. IEEE Geosci Remote Sens Lett 17(11):1948–1952
Garea AS, Heras DB, Argüello F (2019) Caffe CNN-based classification of hyperspectral images on GPU. J Supercomput 75:1065–1077
Zhou F, Hang R, Liu Q, Yuan X (2019) Hyperspectral image classification using spectral–spatial LSTMS. Neurocomputing 328:39–47
Li K, Wang M, Liu Y, Yu N, Lan W (2019) A novel method of hyperspectral data classification based on transfer learning and deep belief network. Appl Sci 9(7):1379
Zhong P, Gong Z, Li S, Schönlieb C-B (2017) Learning to diversify deep belief networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 55(6):3516–3530
Liu B, Yu P, Zhang X, Yu A, Fu Q, Wei X (2017) Supervised deep feature extraction for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56(4):1909–1921
Qiu Q, Wu X, Liu Z, Tang B, Zhao Y, Wu X, Zhu H, Xin Y (2017) Survey of supervised classification techniques for hyperspectral images. Sens Rev 37(3):371–382
Ranjan P, Girdhar A (2022) Xcep-dense: a novel lightweight extreme inception model for hyperspectral image classification. Int J Remote Sens 43(14):5204–5230
Ranjan P, Kumar R, Girdhar A (2023) Recent CNN advancements for stratification of hyperspectral images. In: 2023 6th International conference on information systems and computer networks (ISCON), pp 1–5. IEEE
Zhan Y, Hu D, Wang Y, Yu X (2017) Semisupervised hyperspectral image classification based on generative adversarial networks. IEEE Geosci Remote Sens Lett 15(2):212–216
Ranjan P, Girdhar A (2024) Deep Siamese network with handcrafted feature extraction for hyperspectral image classification. Multimed Tools Appl 83(1):2501–2526
Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv (CSUR) 53(3):1–34
Liu S, Shi Q, Zhang L (2020) Few-shot hyperspectral image classification with unknown classes using multitask deep learning. IEEE Trans Geosci Remote Sens 59(6):5085–5102
Mei S, Ji J, Geng Y, Zhang Z, Li X, Du Q (2019) Unsupervised spatial-spectral feature learning by 3d convolutional autoencoder for hyperspectral classification. IEEE Trans Geosci Remote Sens 57(9):6808–6820
Song W, Li S, Fang L, Lu T (2018) Hyperspectral image classification with deep feature fusion network. IEEE Trans Geosci Remote Sens 56(6):3173–3184
Chen Y, Jiang H, Li C, Jia X, Ghamisi P (2016) Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans Geosci Remote Sens 54(10):6232–6251
Xu Y, Zhang L, Du B, Zhang F (2018) Spectral–spatial unified networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56(10):5893–5909
Zhong Z, Li J, Luo Z, Chapman M (2017) Spectral–spatial residual network for hyperspectral image classification: a 3-d deep learning framework. IEEE Trans Geosci Remote Sens 56(2):847–858
Li Z, Ming L, Chen Y, Xu Y, Li W, Du Q (2022) Deep cross-domain few-shot learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 60:1–18
Xue Z, Zhou Y, Du P (2022) S3net: spectral–spatial Siamese network for few-shot hyperspectral image classification. IEEE Trans Geosci Remote Sens 60:1–19
Xue Z, Liu Z, Zhang M (2023) DSR-GCN: Differentiated-scale restricted graph convolutional network for few-shot hyperspectral image classification. IEEE Trans Geosci Remote Sens 61:1–18
Xue Z, Zhu T, Zhou Y, Zhang M (2022) Bag-of-features-driven spectral–spatial Siamese neural network for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 16:1085–1099
Huang L, Chen Y (2020) Dual-path Siamese CNN for hyperspectral image classification with limited training samples. IEEE Geosci Remote Sens Lett 18(3):518–522
Jia S, Jiang S, Lin Z, Xu M, Sun W, Huang Q, Zhu J, Jia X (2021) A semisupervised Siamese network for hyperspectral image classification. IEEE Trans Geosci Remote Sens 60:1–17
Jiang S, Jia S (2021) A 3d lightweight siamese network for hyperspectral image classification with limited samples. In: 2021 10th international conference on computing and pattern recognition, pp 142–148
Deng F, Pu S, Chen X, Shi Y, Yuan T, Pu S (2018) Hyperspectral image classification with capsule network using limited training samples. Sensors 18(9):3153
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507
BBengio Y, Lamblin P, Popovici D, Larochelle H (2006) Greedy layer-wise training of deep networks. In: Advances in neural information processing systems, vol 19
Chen Y, Lin Z, Zhao X, Wang G, Gu Y (2014) Deep learning-based classification of hyperspectral data. IEEE J Sel Top Appl Earth Obs Remote Sens 7(6):2094–2107
Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794–7803
Wang L, Wang L, Wang Q, Atkinson PM (2021) SSA-SiamNet: spectral–spatial-wise attention-based Siamese network for hyperspectral image change detection. IEEE Trans Geosci Remote Sens 60:1–18
Funding
No specific grant was received for this research from any public, commercial, or non-profit funding agency.
Author information
Authors and Affiliations
Contributions
Pallavi Ranjan conceived the idea, performed implementation, conducted experiments, and wrote the original manuscript. Rajeev Kumar performed writing—review and editing. Ashish Girdhar identified the problem and provided guidance throughout the project.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ranjan, P., Kumar, R. & Girdhar, A. A 3D-convolutional-autoencoder embedded Siamese-attention-network for classification of hyperspectral images. Neural Comput & Applic 36, 8335–8354 (2024). https://doi.org/10.1007/s00521-024-09527-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-024-09527-y