Skip to main content

Deep mixed precision for hyperspectral image classification


Hyperspectral images (HSIs) record scenes at different wavelength channels, providing detailed spatial and spectral information. How to storage and process this high-dimensional data plays a vital role in many practical applications, where classification technologies have emerged as excellent processing tools. However, their high computational complexity and energy requirements bring some challenges. Adopting low-power consumption architectures and deep learning (DL) approaches has to provide acceptable computing capabilities without reducing accuracy demand. However, most DL architectures employ single-precision (FP32) to train models, and some big DL architectures will have a limitation on memory and computation resources. This can negatively affect the network learning process. This letter leads these challenges by using mixed precision into DL architectures for HSI classification to speed up the training process and reduce the memory consumption/access. Proposed models are evaluated on four widely used data sets. Also, low and high-power consumption devices are compared, considering NVIDIA Jetson Xavier and Titan RTX GPUs, to evaluate the proposal viability in on-board processing devices. Obtained results demonstrate the efficiency and effectiveness of these models within HSI classification task for both devices. Source codes:

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3


  1. 1.

    Bioucas-Dias JM, Plaza A, Camps-Valls G, Scheunders P, Nasrabadi N, Chanussot J (2013) Hyperspectral remote sensing data analysis and future challenges. IEEE Geosci Remote Sens Mag 1(2):6–36

    Article  Google Scholar 

  2. 2.

    Fang B, Li Y, Zhang H, Chan JCW (2020) Collaborative learning of lightweight convolutional neural network and deep clustering for hyperspectral image semi-supervised classification with limited training samples. ISPRS J Photogram Remote Sens 161:164–178.

    Article  Google Scholar 

  3. 3.

    Green RO, Eastwood ML, Sarture CM, Chrien TG, Aronsson M, Chippendale BJ, Faust JA, Pavri BE, Chovit CJ, Solis M et al (1998) Imaging spectroscopy and the airborne visible/infrared imaging spectrometer (aviris). Remote Sens Environ 65(3):227–248

    Article  Google Scholar 

  4. 4.

    Haut JM, Alcolea A, Paoletti ME, Plaza J, Resano J, Plaza A (2020) Gpu-friendly neural networks for remote sensing scene classification. IEEE Geosci Remote Sens Lett.

    Article  Google Scholar 

  5. 5.

    Haut JM, Bernabé S, Paoletti ME, Fernandez-Beltran R, Plaza A, Plaza J (2018) Low-high-power consumption architectures for deep-learning models applied to hyperspectral image classification. IEEE Geosci Remote Sens Lett 16(5):776–780

    Article  Google Scholar 

  6. 6.

    Haut JM, Paoletti M, Plaza J, Plaza A (2017) Cloud implementation of the k-means algorithm for hyperspectral image analysis. J Supercomput 73(1):514–529

    Article  Google Scholar 

  7. 7.

    Haut JM, Paoletti ME, Plaza J, Li J, Plaza A (2018) Active learning with convolutional neural networks for hyperspectral image classification using a new bayesian approach. IEEE Trans Geosci Remote Sens 56(11):6440–6461

    Article  Google Scholar 

  8. 8.

    Haut JM, Paoletti ME, Plaza J, Plaza A, Li J (2019) Hyperspectral image classification using random occlusion data augmentation. IEEE Geosci Remote Sens Lett 16(11):1751–1755

    Article  Google Scholar 

  9. 9.

    Jia X, Song S, He W, Wang Y, Rong H, Zhou F, Xie L, Guo Z, Yang Y, Yu L et al (2018) Highly scalable deep learning training system with mixed-precision: training imagenet in four minutes. arXiv preprint arXiv:1807.11205

  10. 10.

    Jia Z, Maggioni M, Smith J, Scarpazza DP (2019) Dissecting the nvidia turing t4 gpu via microbenchmarking. arXiv preprint arXiv:1903.07486

  11. 11.

    Kim D, Kwon Y, Liu P, Kim IL, Perry DM, Zhang X, Rodriguez-Rivera G (2016) Apex: automatic programming assignment error explanation. ACM SIGPLAN Notices 51(10):311–327

    Article  Google Scholar 

  12. 12.

    Kunkel B, Blechinger F, Lutz R, Doerffer R, Van der Piepen H, Schroder M (1988) Rosis (reflective optics system imaging spectrometer)-a candidate instrument for polar platform missions. In: Optoelectronic technologies for remote sensing from space, vol 868. International Society for Optics and Photonics, pp 134–141

  13. 13.

    Lanaras C, Baltsavias E, Schindler K (2015) Hyperspectral super-resolution by coupled spectral unmixing. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3586–3594

  14. 14.

    Li P, Han L, Tao X, Zhang X, Grecos C, Plaza A, Ren P (2020) Hashing nets for hashing: a quantized deep learning to hash framework for remote sensing image retrieval. IEEE Trans Geosci Remote Sens 58(10):7331–7345.

    Article  Google Scholar 

  15. 15.

    Lofqvist M, Cano J (2020) Accelerating deep learning applications in space. In: The 34th Annual Small Satellite Conference

  16. 16.

    Lu J, Lu S, Wang Z, Fang C, Lin J, Wang Z, Du L (2019) Training deep neural networks using posit number system. In: 32nd IEEE International System-on-Chip Conference (SOCC), pp 62–67.

  17. 17.

    Micikevicius P, Narang S, Alben J, Diamos G, Elsen E, Garcia D, Ginsburg B, Houston M, Kuchaiev O, Venkatesh G, Wu H (2018) Mixed precision training. In: International Conference on Learning Representations

  18. 18.

    Paoletti M, Haut J, Plaza J, Plaza A (2018) A new deep convolutional neural network for fast hyperspectral image classification. ISPRS J Photogramm Remote Sens 145:120–147

    Article  Google Scholar 

  19. 19.

    Paoletti ME, Haut JM, Fernandez-Beltran R, Plaza J, Plaza A, Li J, Pla F (2018) Capsule networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(4):2145–2160

    Article  Google Scholar 

  20. 20.

    Paoletti ME, Haut JM, Fernandez-Beltran R, Plaza J, Plaza AJ, Pla F (2018) Deep pyramidal residual networks for spectral-spatial hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(2):740–754

    Article  Google Scholar 

  21. 21.

    Paoletti ME, Haut JM, Sidonio N, Plaza J, Plaza A (2021) Ghostnet for hyperspectral image classification. IEEE Trans Geosci Remote Sens.

    Article  Google Scholar 

  22. 22.

    Paoletti ME, Haut JM, Tao X, Plaza J, Plaza A (2020) Flop-reduction through memory allocations within cnn for hyperspectral image classification. IEEE Trans Geosci Remote Sens.

    Article  Google Scholar 

  23. 23.

    Roy SK, Chatterjee S, Bhattacharyya S, Chaudhuri BB, Platoš J (2020) Lightweight spectral-spatial squeeze-and- excitation residual bag-of-features learning for hyperspectral classification. IEEE Trans Geosci Remote Sens 58(8):5277–5290.

    Article  Google Scholar 

  24. 24.

    Tao X, Cui T, Ren P (2019) Cofactor-based efficient endmember extraction for green algae area estimation. IEEE Geosci Remote Sens Lett 16(6):849–853

    Article  Google Scholar 

  25. 25.

    Yu J, Huang T (2019) Autoslim: towards one-shot architecture search for channel numbers. arXiv preprint arXiv:1903.11728

  26. 26.

    Yue J, Zhao W, Mao S, Liu H (2015) Spectral-spatial classification of hyperspectral images using deep convolutional neural networks. Remote Sens Lett 6(6):468–477

    Article  Google Scholar 

Download references


Supported by FEDER and Junta de Extremadura (GR18060).

Author information



Corresponding author

Correspondence to J. M. Haut.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Paoletti, M.E., Tao, X., Haut, J.M. et al. Deep mixed precision for hyperspectral image classification. J Supercomput 77, 9190–9201 (2021).

Download citation


  • Hyperspectral image
  • Deeplearning
  • Mixed precision