[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

An autonomous lightweight model for aerial scene classification under labeled sample scarcity

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Aerial scene classification using convolutional neural network (CNN) has gained substantial research interest during last few years. The performance of these deep models is found to improve more when the spatial relationships among the scene features are explicitly modelled using capsule network (CapsNet). However, the combined CNN and CapsNet-based scene classifiers are not only computationally intensive but also often suffer from over-parameterization, leading to remarkable performance deterioration under scarcity of labeled samples. In order to address this issue, we propose a lightweight as well as autonomous CapsNet model which auto-prunes the unnecessary weights/parameters during network learning/training phase, and eventually reduces the computational cost. The efficacy of our lightweight autonomous CapsNet is evaluated after embedding this into PReLim, a recently developed paradigm for remote sensing scene classification under observed sample limitation. Experiments on three benchmark datasets show that our proposed lightweight PReLim (LW-PReLim) is able to attain state-of-the-art accuracy even with 25% less CapsNet parameter count.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Availability of data and material

Datasets used are publicly available.

Code Availability

Not applicable.

Notes

  1. https://captain-whu.github.io/AID/

References

  1. Wang J, Yu J, He Z (2022) ARFP: A novel adaptive recursive feature pyramid for object detection in aerial images. Appl Intell 1–16

  2. Sawant SS, Bauer J, Erick F et al (2022) An optimal-score-based filter pruning for deep convolutional neural networks. Appl Intell 1–23

  3. Huang K, Liu X, Fu S et al (2019) A lightweight privacy-preserving CNN feature extraction framework for mobile sensing. IEEE Trans Dependable Secure Comput 18(3):1441–1455

    Google Scholar 

  4. Liang T, Glossner J, Wang L et al (2021) Pruning and quantization for deep neural network acceleration: A survey. Neurocomputing 461:370–403

    Article  Google Scholar 

  5. Guo X, Hou B, Ren B et al (2022) Network pruning for remote sensing images classification based on interpretable CNNs. IEEE Trans Geosci Remote Sens 60:1–15. https://doi.org/10.1109/TGRS.2021.3077062

    Article  Google Scholar 

  6. Fan Y, Pang W, Lu S (2021) HFPQ: deep neural network compression by hardware-friendly pruning-quantization. Appl Intell 51(10):7016–7028

    Article  Google Scholar 

  7. Li Z, Liu X, Zhao Y et al (2021) A lightweight multi-scale aggregated model for detecting aerial images captured by UAVS. J Vis Commun Image Represent 77:103058. https://doi.org/10.1016/j.jvcir.2021.103058

    Article  Google Scholar 

  8. Ji H, Yang H, Gao Z et al (2022) Few-shot scene classification using auxiliary objectives and transductive inference. IEEE Geosci Remote Sens Lett 19:1–5

    Article  Google Scholar 

  9. Cui Z, Yang W, Chen L et al (2022) MKN: Metakernel networks for few shot remote sensing scene classification. IEEE Trans Geosci Remote Sens 60:1–11

    Google Scholar 

  10. Xiong Y, Xu K, Dou Y et al (2021) Wrmatch: Improving fixmatch with weighted nuclear-norm regularization for few-shot remote sensing scene classification. IEEE Trans Geosci Remote Sens 60:1–14

  11. Ma D, Tang P, Zhao L (2019) SiftingGAN: Generating and sifting labeled samples to improve the remote sensing image scene classification baseline in vitro. IEEE Geosci Remote Sens Lett 16(7):1046–1050

    Article  Google Scholar 

  12. Gómez P, Meoni G (2021) MSMatch: Semisupervised multispectral scene classification with few labels. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14:11643–11654

    Article  Google Scholar 

  13. Shi C, Zhang X, Sun J et al (2022) Remote sensing scene image classification based on self-compensating convolution neural network. Remote Sens 14(3). https://doi.org/10.3390/rs14030545

  14. Singh CK, Gangwar VK, Majumder A et al (2020) A light-weight deep feature based capsule network. In: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1–8

  15. Jeong M, Kim C (2021) A parameter efficient multi-scale capsule network. In: 2021 IEEE International Conference on Image Processing (ICIP). pp 739–743. https://doi.org/10.1109/ICIP42928.2021.9506364

  16. Valerio L, Nardini FM, Passarella A et al (2022) Dynamic hard pruning of neural networks at the edge of the internet. J Netw Comput Appl 200(103):330

    Google Scholar 

  17. Tang Y, Wang Y, Xu Y et al (2021) Manifold regularized dynamic network pruning. In: Proceedings of the IEEE/CVF Conf. on Comp. Vision and Pattern Recognition. pp 5018–5028

  18. Das M, Pratama M, Ashfahani A, et al (2019) FERNN: A fast and evolving recurrent neural network model for streaming data classification. In: 2019 International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1–8

  19. Ashfahani A, Pratama M, Lughofer E et al (2020) DEVDAN: Deep evolving denoising autoencoder. Neurocomputing 390:297–314

    Article  Google Scholar 

  20. Das M, Pratama M, Ghosh SK (2020) SARDINE: A self-adaptive recurrent deep incremental network model for spatio-temporal prediction of remote sensing data. ACM Transactions on Spatial Algorithms and Systems (TSAS) 6(3):1–26

    Article  Google Scholar 

  21. Das M (2020) Online prediction of derived remote sensing image time series: an autonomous machine learning approach. In: 2020 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, pp 1496–1499

  22. Dutta S, Das M (2021) PReLim: a modeling paradigm for remote sensing image scene classification under limited labeled samples. In: In 9th International Conference on Pattern Recognition and Machine Intelligence, December 2021, Kolkata, India. Springer

  23. He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition. pp 770–778

  24. Li B, Su W, Wu H et al (2019) Aggregated deep fisher feature for VHR remote sensing scene classification. IEEE J Sel Top Appl Earth Obs Remote Sens 12(9):3508–3523

    Article  Google Scholar 

  25. Cheng G, Han J, Lu X (2017) Remote sensing image scene classification: Benchmark and state of the art. Proc IEEE 105(10):1865–1883

    Article  Google Scholar 

  26. Qi K, Yang C, Hu C et al (2021) Rotation invariance regularization for remote sensing image scene classification with convolutional neural networks. Remote Sens 13(4):569

    Article  Google Scholar 

  27. Tang X, Ma Q, Zhang X et al (2021) Attention consistent network for remote sensing scene classification. IEEE J Sel Top Appl Earth Obs Remote Sens 14:2030–2045

    Article  Google Scholar 

  28. Xu C, Zhu G, Shu J (2021) A lightweight and robust lie group-convolutional neural networks joint representation for remote sensing scene classification. IEEE Trans Geosci Remote Sens 60:1-15

    Google Scholar 

Download references

Funding

This work was supported by INSPIRE Faculty Fellowship Research Grant [DST/INSPIRE/04/2019/001670 to M.D.] by the Department of Science and Technology, India.

Author information

Authors and Affiliations

  1. Machine Intelligence Unit, Indian Statistical Institute, Kolkata, 203 B. T. Road, Kolkata, 700108, West Bengal, India

    Suparna Dutta

  2. Department of Computer Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, 826004, Jharkhand, India

    Monidipa Das

Authors
  1. Suparna Dutta
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Monidipa Das
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Suparna Dutta: Software, Implementation, Validation, Investigation, Data curation, Writing- Original draft preparation. Monidipa Das: Conceptualization, Design of study, Writing - Drafting, Review & Editing, Supervision, Project administration, Funding acquisition.

Corresponding author

Correspondence to Monidipa Das.

Ethics declarations

Ethics approval

Not applicable.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dutta, S., Das, M. An autonomous lightweight model for aerial scene classification under labeled sample scarcity. Appl Intell 53, 22216–22227 (2023). https://doi.org/10.1007/s10489-023-04694-2

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-023-04694-2

Keywords

Search

Navigation