Skip to main content
SpringerLink
Log in

A comprehensive review: active learning for hyperspectral image classifications

  • REVIEW
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

Abstract

Advanced Hyperspectral image sensors can capture high-resolution land cover images. Many supervised Machine learning (ML) and Deep learning (DL) algorithms succeeded in the Hyperspectral image classification for various applications. Scientific findings reveal that supervised learning methods’ performance heavily depends on training set size, i.e., labelled by the ground truth collection. Labelling a large volume of hyperspectral images is tedious and time-consuming. Research in Active learning (AL) aims to determine the minimal set of samples for labelling, ensuring that model performance is unaffected by training using a minimal set of samples. This article examined fundamental AL and cutting-edge methods used for hyperspectral image classifications. This article also focuses on the cutting-edge approach known as Active Deep Learning (ADL). ADL combines the strong discriminative capabilities of the deep learning model with active learning. This article examined the use of ADL for the Hyperspectral images (HSIs) classifications and reviewed opportunities and challenges. At last, the experiment illustrates and evaluates the integration of the DL model with several AL approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

This manuscript has no associated data.

References

  • Abdi G, Samadzadegan F, Reinartz P (2017) Spectral–spatial feature learning for hyperspectral imagery classification using deep stacked sparse autoencoder. Journal of Applied Remote Sensing 11(4):042604

    Google Scholar 

  • Abe N (1998) Query learning strategies using boosting and bagging. Proceedings of the Fifteenth International Conference on Machine Learning (ICML98) pp 1–9

  • Adão T, Hruška J, Pádua L et al (2017) Hyperspectral imaging: A review on uav-based sensors, data processing and applications for agriculture and forestry. Remote Sensing 9(11):1110

    Google Scholar 

  • Ahmad M, Shabbir S, Oliva D et al (2020) Spatial-prior generalized fuzziness extreme learning machine autoencoder-based active learning for hyperspectral image classification. Optik 206:163712

    Google Scholar 

  • Ahmad M (2020) Fuzziness-based spatial-spectral class discriminant information preserving active learning for hyperspectral image classification. arXiv preprint arXiv:200514236

  • Azadegan A, Porobic L, Ghazinoory S et al (2011) Fuzzy logic in manufacturing: A review of literature and a specialized application. Int J Prod Econ 132(2):258–270

    Google Scholar 

  • Cai R, Liu C, Li J (2021) Phase-induced gabor-based multiview active learning for hyperspectral image classification. IEEE Geosci Remote Sens Lett 19:1–5

    Google Scholar 

  • Cao X, Yao J, Fu X et al (2020a) An enhanced 3-d discrete wavelet transform for hyperspectral image classification. IEEE Geosci Remote Sens Lett 18(6):1104–1108

    Google Scholar 

  • Cao X, Yao J, Xu Z et al (2020b) Hyperspectral image classification with convolutional neural network and active learning. IEEE Trans Geosci Remote Sens 58(7):4604–4616

    Google Scholar 

  • Chen Y, Jiang H, Li C et al (2016) Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans Geosci Remote Sens 54(10):6232–6251

    Google Scholar 

  • Crawford MM, Tuia D, Yang HL (2013) Active learning: Any value for classification of remotely sensed data? Proc IEEE 101(3):593–608

    Google Scholar 

  • Culotta A, McCallum A (2005) Reducing labeling effort for structured prediction tasks. In: AAAI, pp 746–751

  • Datta D, Mallick PK, Bhoi AK et al (2022) Hyperspectral image classification: Potentials, challenges, and future directions. Comput Intell Neurosci 2022:1–36

    Google Scholar 

  • Demir B, Persello C, Bruzzone L (2010) Batch-mode active-learning methods for the interactive classification of remote sensing images. IEEE Trans Geosci Remote Sens 49(3):1014–1031

    Google Scholar 

  • Deng L, Yu D et al (2014) Deep learning: methods and applications. Foundations and Trends in Signal Processing 7(3–4):197–387

    Google Scholar 

  • Deng C, Xue Y, Liu X et al (2018) Active transfer learning network: A unified deep joint spectral–spatial feature learning model for hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(3):1741–1754

    Google Scholar 

  • Di W, Crawford MM (2010) Multi-view adaptive disagreement based active learning for hyperspectral image classification. In: 2010 IEEE International Geoscience and Remote Sensing Symposium, IEEE, pp 1374–1377

  • Di W, Crawford MM (2011) View generation for multiview maximum disagreement based active learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 50(5):1942–1954

    Google Scholar 

  • Ding C, Zheng M, Chen F et al (2022) Hyperspectral image classification promotion using clustering inspired active learning. Remote Sensing 14(3):596

    Google Scholar 

  • Dong S, Quan Y, Feng W et al (2021) A pixel cluster cnn and spectralspatial fusion algorithm for hyperspectral image classification with smallsize training samples. IEEE J Sel Top Appl Earth Obs Remote Sens 14:4101–4114

    Google Scholar 

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

    Google Scholar 

  • Feng Y, Yuan Y, Lu X (2017) Learning deep event models for crowd anomaly detection. Neurocomputing 219:548–556

    Google Scholar 

  • Gao AF, Rasmussen B, Kulits P, et al (2021) Generalized unsupervised clustering of hyperspectral images of geological targets in the near infrared. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp 4294–4303

  • Guo J, Zhou X, Li J et al (2016) Superpixel-based active learning and online feature importance learning for hyperspectral image analysis. IEEE J Sel Top Appl Earth Obs Remote Sens 10(1):347–359

    Google Scholar 

  • Hajiani F, Parhizgar N, Keshavarz A (2021) Hyperspectral image classification using cluster based graph regularized low rank representation and dictionary learning. Neurocomputing 462:208–220

    Google Scholar 

  • Haußmann M, Hamprecht FA, Kandemir M (2019) Deep active learning with adaptive acquisition. arXiv preprint arXiv:190611471

  • Haut JM, Paoletti ME, Plaza J et al (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

    Google Scholar 

  • He Z, Liu H, Wang Y et al (2017) Generative adversarial networks-based semisupervised learning for hyperspectral image classification. Remote Sensing 9(10):1042

    Google Scholar 

  • He X, Chen Y, Ghamisi P (2019) Heterogeneous transfer learning for hyperspectral image classification based on convolutional neural network. IEEE Trans Geosci Remote Sens 58(5):3246–3263

    Google Scholar 

  • Houlsby N, Huszár F, Ghahramani Z, et al (2011) Bayesian active learning for classification and preference learning. arXiv preprint arXiv:11125745

  • Hsu WN, Lin HT (2015) Active learning by learning. In: Twenty-Ninth AAAI conference on artificial intelligence

  • Hu J, He Z, Li J et al (2018) 3d-gabor inspired multiview active learning for spectral-spatial hyperspectral image classification. Remote Sensing 10(7):1070

    Google Scholar 

  • Jamshidpour N, Safari A, Homayouni S (2020) A ga-based multi-view, multilearner active learning framework for hyperspectral image classification. Remote Sensing 12(2):297

    Google Scholar 

  • Jia S, Jiang S, Lin Z et al (2021) A survey: Deep learning for hyperspectral image classification with few labeled samples. Neurocomputing 448:179–204

    Google Scholar 

  • Joshi AJ, Porikli F, Papanikolopoulos N (2009) Multi-class active learning for image classification. In: 2009 ieee conference on computer vision and pattern recognition, IEEE, pp 2372–2379

  • Kahraman S, Bacher R (2021) A comprehensive review of hyperspectral data fusion with lidar and sar data. Annu Rev Control 51:236–253

    Google Scholar 

  • Kalita I, Kumar RNS, Roy M (2021) Deep learning-based cross-sensor domain adaptation under active learning for land cover classification. IEEE Geosci Remote Sens Lett 19:1–5

    Google Scholar 

  • Khan MJ, Khan HS, Yousaf A et al (2018) Modern trends in hyperspectral image analysis: A review. Ieee Access 6:14118–14129

    Google Scholar 

  • Konyushkova K, Sznitman R, Fua P (2017) Learning active learning from data. Advances in Neural Information Processing Systems 30

  • Lee H, Kwon H (2017) Going deeper with contextual cnn for hyperspectral image classification. IEEE Trans Image Process 26(10):4843–4855

    Google Scholar 

  • Lei Z, Zeng Y, Liu P et al (2021) Active deep learning for hyperspectral image classification with uncertainty learning. IEEE Geosci Remote Sens Lett 19:1–5

    Google Scholar 

  • Leskes B (2005) The value of agreement, a new boosting algorithm. In: Auer Peter, Meir Ron (eds) International conference on computational learning theory. Springer, Berlin, pp 95–110

    Google Scholar 

  • Lewis DD, Catlett J (1994) Heterogeneous uncertainty sampling for supervised learning. In: Machine learning proceedings 1994. Elsevier, p 148–156

  • Li Z, Liu M, Chen Y et al (2021) Deep cross-domain few-shot learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 60:1–18

    Google Scholar 

  • Li J (2015) Active learning for hyperspectral image classification with a stacked autoencoders based neural network. In: 2015 7thWorkshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), IEEE, pp 1–4

  • Liang X, Zhang Y, Zhang J (2021) Attention multisource fusion-based deep few-shot learning for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 14:8773–8788

    Google Scholar 

  • Lin J, Zhao L, Li S et al (2018) Active-learning-incorporated deep transfer learning for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 11(11):4048–4062

    Google Scholar 

  • Liu P, Zhang H, Eom KB (2016) Active deep learning for classification of hyperspectral images. IEEE J Sel Top Appl Earth Obs Remote Sens 10(2):712–724

    Google Scholar 

  • Liu C, He L, Li Z et al (2017) Feature-driven active learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56(1):341–354

    Google Scholar 

  • Liu B, Yu X, Yu A et al (2018a) Spectral-spatial classification of hyperspectral imagery based on recurrent neural networks. Remote Sens Lett 9(12):1118–1127

    Google Scholar 

  • Liu B, Yu X, Yu A et al (2018b) Deep few-shot learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(4):2290–2304

    Google Scholar 

  • Liu C, Li J, He L (2018c) Superpixel-based semisupervised active learning for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 12(1):357–370

    Google Scholar 

  • Liu X, Hu Q, Cai Y et al (2020) Extreme learning machine-based ensemble transfer learning for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 13:3892–3902

    Google Scholar 

  • Lu T, Li S, Benediktsson JA (2017) Iterative clustering based active learning for hyperspectral image classification. In: 2017 IEEE international geoscience and remote sensing symposium (IGARSS), IEEE, pp 3664–3667

  • Lu Q, Wei L (2021) Multiscale superpixel-based active learning for hyperspectral image classification. IEEE Geosci Remote Sens Lett 19:1–5

    Google Scholar 

  • Luo T, Kramer K, Goldgof DB, et al (2005) Active learning to recognize multiple types of plankton. J Mach Learn Res 6(4)

  • Ma L, Ma A, Ju C et al (2016) Graph-based semi-supervised learning for spectral-spatial hyperspectral image classification. Pattern Recognit Lett 83:133–142

    Google Scholar 

  • MacKay DJ (1992) Information-based objective functions for active data selection. Neural Comput 4(4):590–604

    Google Scholar 

  • Melgani F, Bruzzone L (2004) Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Remote Sens 42(8):1778–1790

    Google Scholar 

  • Mnih V, Kavukcuoglu K, Silver D, et al (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:13125602

  • Mou L, Ghamisi P, Zhu XX (2017) Deep recurrent neural networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 55(7):3639–3655

    Google Scholar 

  • Moughal T (2013) Hyperspectral image classification using support vector machine. J Phys Conf Ser 439:012042 (IOP Publishing)

    Google Scholar 

  • Mu C, Liu J, Liu Y et al (2020) Hyperspectral image classification based on active learning and spectral-spatial feature fusion using spatial coordinates. IEEE Access 8:6768–6781

    Google Scholar 

  • Murphy JM (2020) Spatially regularized active diffusion learning for highdimensional images. Pattern Recogn Lett 135:213–220

    Google Scholar 

  • Muslea I, Minton S, Knoblock CA (2006) Active learning with multiple views. J Artif Intell Res 27:203–233

    Google Scholar 

  • Paoletti ME, Haut JM, Plaza J, et al (2020) Training capsnets via active learning for hyperspectral image classification. In: IGARSS 2020–2020 IEEE International Geoscience and Remote Sensing Symposium, IEEE, pp 40–43

  • Pasolli E, Melgani F, Bazi Y (2010) Support vector machine active learning through significance space construction. IEEE Geosci Remote Sens Lett 8(3):431–435

    Google Scholar 

  • Patel U, Dave H, Patel V (2021) Hyperspectral image classification using uncertainty and diversity based active learning. Scalable Comput Pract Exper 22(3):283–293

    Google Scholar 

  • Patel U, Dave H, Patel V (2020) Hyperspectral image classification using semisupervised learning with label propagation. In: 2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS), IEEE, pp 205–208

  • Priya T, Prasad S, Wu H (2015) Superpixels for spatially reinforced bayesian classification of hyperspectral images. IEEE Geosci Remote Sens Lett 12(5):1071–1075

    Google Scholar 

  • Qian Y, Ye M, Zhou J (2012) Hyperspectral image classification based on structured sparse logistic regression and three-dimensional wavelet texture features. IEEE Trans Geosci Remote Sens 51(4):2276–2291

    Google Scholar 

  • Qin Y, Bruzzone L, Li B et al (2019) Cross-domain collaborative learning via cluster canonical correlation analysis and random walker for hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(6):3952–3966

    Google Scholar 

  • Ren P, Xiao Y, Chang X et al (2021) A survey of deep active learning. ACM Comput Surv (CSUR) 54(9):1–40

    Google Scholar 

  • Rottmann M, Kahl K, Gottschalk H (2018) Deep bayesian active semisupervised learning. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, pp 158–164

  • Roy SK, Krishna G, Dubey SR et al (2019) Hybridsn: Exploring 3-d–2-d cnn feature hierarchy for hyperspectral image classification. IEEE Geosci Remote Sens Lett 17(2):277–281

    Google Scholar 

  • Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. Advances in Neural Information Processing Systems 30

  • Salem MB, Ettabaa KS, Bouhlel MS (2016) Hyperspectral image feature selection for the fuzzy c-means spatial and spectral clustering. In: 2016 International Image Processing, Applications and Systems (IPAS), IEEE, pp 1–5

  • Samat A, Li J, Liu S et al (2016) Improved hyperspectral image classification by active learning using pre-designed mixed pixels. Pattern Recogn 51:43–58

    Google Scholar 

  • Samat A, Li J, Lin C et al (2019) Edge gradient-based active learning for hyperspectral image classification. IEEE Geosci Remote Sens Lett 17(9):1588–1592

    Google Scholar 

  • Sawant SS, Prabukumar M (2020) A review on graph-based semi-supervised learning methods for hyperspectral image classification. Egypt J Remote Sens Space Sci 23(2):243–248

    Google Scholar 

  • Sener O, Savarese S (2017) Active learning for convolutional neural networks: A core-set approach. arXiv preprint arXiv:170800489

  • Seung HS, Opper M, Sompolinsky H (1992) Query by committee. In: Proceedings of the fifth annual workshop on Computational learning theory, pp 287–294

  • Stutz D, Hermans A, Leibe B (2018) Superpixels: An evaluation of the stateof-the-art. Comput vis Image Underst 166:1–27

    Google Scholar 

  • Sun Y, Li J, Wang W, et al (2016) Active learning based autoencoder for hyperspectral imagery classification. In: 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE, pp 469–472

  • Thoreau R, Achard V, Risser L et al (2022) Active learning for hyperspectral image classification: A comparative review. IEEE Geosci Remote Sens Mag 10(3):256–278

    Google Scholar 

  • Tran T, Do TT, Reid I, et al (2019) Bayesian generative active deep learning. In: International Conference on Machine Learning, PMLR, pp 6295–6304

  • Tuia D, Ratle F, Pacifici F et al (2009) Active learning methods for remote sensing image classification. IEEE Trans Geosci Remote Sens 47(7):2218–2232

    Google Scholar 

  • Tuia D, Volpi M, Copa L et al (2011) A survey of active learning algorithms for supervised remote sensing image classification. IEEE J Sel Top Signal Process 5(3):606–617

    Google Scholar 

  • Tuia D, Muñoz-Marí J, Camps-Valls G (2012) Remote sensing image segmentation by active queries. Pattern Recogn 45(6):2180–2192

    Google Scholar 

  • Wang G, Ren P (2020) Hyperspectral image classification with feature-oriented adversarial active learning. Remote Sens 12(23):3879

    Google Scholar 

  • Wang J, Guo S, Huang R et al (2021a) Dual-channel capsule generation adversarial network for hyperspectral image classification. IEEE Trans Geosci Remote Sens 60:1–16

    Google Scholar 

  • Wang X, Tan K, Pan C et al (2022) Active deep feature extraction for hyperspectral image classification based on adversarial learning. IEEE Geosci Remote Sens Lett 19:1–5

    Google Scholar 

  • Wang X, Xing C, Feng Y, et al (2021b) A novel hyperspectral image change detection framework based on 3d-wavelet domain active convolutional neural network. In: 2021b IEEE International Geoscience and Remote Sensing Symposium IGARSS, IEEE, pp 4332–4335

  • Wu H, Prasad S (2017) Semi-supervised deep learning using pseudo labels for hyperspectral image classification. IEEE Trans Image Process 27(3):1259–1270

    Google Scholar 

  • Xing C, Ma L, Yang X (2016) Stacked denoise autoencoder based feature extraction and classification for hyperspectral images. J Sens 2016:1–10

    Google Scholar 

  • Xu X, Li J, Li S (2017) Multiview intensity-based active learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56(2):669–680

    Google Scholar 

  • Xu M, Zhao Q, Jia S (2021) Multiview spatial-spectral active learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 60:1–15

    Google Scholar 

  • Xue Z, Zhou S, Zhao P (2018) Active learning improved by neighborhoods and superpixels for hyperspectral image classification. IEEE Geosci Remote Sens Lett 15(3):469–473

    Google Scholar 

  • Yang L, MacEachren AM, Mitra P et al (2018) Visually-enabled active deep learning for (geo) text and image classification: a review. ISPRS Int J Geo Inf 7(2):65

    Google Scholar 

  • Zhang Z, Pasolli E, Crawford MM et al (2015) An active learning framework for hyperspectral image classification using hierarchical segmentation. IEEE J Sel Top Appl Earth Obs Remote Sens 9(2):640–654

    Google Scholar 

  • Zhang F, Du B, Zhang L et al (2016a) Hierarchical feature learning with dropout k-means for hyperspectral image classification. Neurocomputing 187:75–82

    Google Scholar 

  • Zhang X, Song Q, Gao Z et al (2016b) Spectral–spatial feature learning using cluster-based group sparse coding for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 9(9):4142–4159

    Google Scholar 

  • Zhang H, Li Y, Zhang Y et al (2017) Spectral-spatial classification of hyperspectral imagery using a dual-channel convolutional neural network. Remote Sens Lett 8(5):438–447

    Google Scholar 

  • Zhang Y, Cao G, Li X et al (2018) Cascaded random forest for hyperspectral image classification. IEEE J Sel Topics Appl Earth Obs Remote Sens 11(4):1082–1094

    Google Scholar 

  • Zhao W, Chen X, Bo Y et al (2019) Semisupervised hyperspectral image classification with cluster-based conditional generative adversarial net. IEEE Geosci Remote Sens Lett 17(3):539–543

    Google Scholar 

  • Zhong Y, Ma A, Soon Ong Y et al (2018) Computational intelligence in optical remote sensing image processing. Appl Soft Comput 64(75):93

    Google Scholar 

  • Zhou X, Prasad S, Crawford MM (2016) Wavelet-domain multiview active learning for spatial-spectral hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 9(9):4047–4059

    Google Scholar 

  • Zhu L, Chen Y, Ghamisi P et al (2018) Generative adversarial networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56(9):5046–5063

    Google Scholar 

  • Zhu JJ, Bento J (2017) Generative adversarial active learning. arXiv preprint arXiv:170207956

Download references

Acknowledgements

We are grateful to the reviewer for their critical and insightful comments. Their feedback has greatly improved the quality of our work, and their dedication and expertise are highly appreciated.

Funding

Funding not obtained for this study.

Author information

Authors and Affiliations

  1. CSE Department, Institute of Technology, Nirma University, Ahmedabad, India

    Usha Patel

  2. IT Department, Vishwakarma Government Engineering College, Gujarat Technological University, Ahmedabad, India

    Vibha Patel

Authors
  1. Usha Patel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Vibha Patel
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Both the author have equally contributed..

Corresponding author

Correspondence to Usha Patel.

Ethics declarations

Competing interests

The authors declare no competing interests.

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Communicated by: H. Babaie

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Patel, U., Patel, V. A comprehensive review: active learning for hyperspectral image classifications. Earth Sci Inform 16, 1975–1991 (2023). https://doi.org/10.1007/s12145-023-01040-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-023-01040-5

Keywords

Search

Navigation