skip to main content
10.1145/3647649.3647668acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicigpConference Proceedingsconference-collections
research-article

Self-Supervised Contrastive Learning Residual Network for Hyperspectral Image Classification Under Limited Labeled Samples

Published: 03 May 2024 Publication History

Abstract

Recently, deep learning methods have achieved impressive results on hyperspectral image (HSI) classification. However, there is a significant challenge in HSI classification tasks in the limited number of labeled samples. Since obtaining labels for HSIs is an expensive and time-consuming task, the number of labeled samples during the training phase is relatively small. The performance of these deep learning methods may be limited when the labeled samples is limited. To solve the small-sample HSI classification problem, a novel approach by integrating self-supervised contrastive learning with residual networks is proposed in this paper. The proposed network firstly adopts a spatial-spectral data augmentation strategy to expand the limited HSI data set and generate new positive and negative sample pairs for training. Then a spectral dimension reduction residual network is conducted to relieve the vanishing gradients and extract spatial-spectral feature on limited labeled samples. The scarcity of labeled data often hinders the effectiveness of traditional classification models. Therefore, a self-supervised contrastive learning framework is designed to focus on the relative relationship between samples to make full use of limited HSI sample information. Experimental results on 2 public HSI datasets demonstrate that the proposal can achieve better performance than existing state-of-the-art methods when training samples is limited.

References

[1]
B. Lu, P. D. Dao, J. Liu, Y. He, and J. Shang, “Recent advances of hyperspectral imaging technology and applications in agriculture,” Remote Sens., 2020, vol. 12, no. 16, pp. 2659-2702.
[2]
X. Yang and Y. Yu, “Estimating soil salinity under various moisture conditions: An experimental study,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 5, pp. 2525-2533, May 2017.
[3]
Wu L, Peng Y, Li C, “Hyperspectral image open set recognition based on the extreme value machine,” AOPC 2020: Display Technology; Photonic MEMS, THz MEMS, and Metamaterials; and AI in Optics and Photonics. SPIE, 2022, vol. 11565, pp. 114-119.
[4]
R. Anand, S. Veni, and J. Ara inth, “Big data challenges in airborne hyperspectral image for urban landuse classification,” in Proc. 2017 Int. Conf. Adv. Comp., Com. and Inf. (ICACCI), 2017, pp. 1808-1814.
[5]
F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens., vol. 42, no. 8, pp. 1778–1790, Aug. 2004.
[6]
P. O. Gislason, J. A. Benediktsson, and J. R. Sveinsson, “Random forests for land cover classification,” Pattern Recognit. Lett., vol. 27, no. 4, pp. 294–300, 2006.
[7]
J. A. Benediktsson, P. H. Swain, and O. K. Ersoy, “Neural network approaches versus statistical methods in classification of multisource remote sensing data,” in Proc. 12th Can. Symp. Remote Sens. Geosci. Remote Sens. Symp., vol. 2, Jul. 1989, pp. 489–492.
[8]
M. Pal, “Extreme-learning-machine-based land cover classification,” Int. J. Remote Sens., vol. 30, no. 14, pp. 3835–3841, 2009.
[9]
S. Dong, P. Wang, K. Abbas, “A survey on deep learning and its applications,” Computer Science Review, 2021, vol. 40.
[10]
S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens., vol. 57, no. 9, pp. 6690–6709, Sep. 2019.
[11]
Li N, Wang Z, “Spatial attention guided residual attention network for hyperspectral image classification,” IEEE Access, vol. 10, pp. 9830-9847, 2022.
[12]
N. Li, Z. Wang, Cheikh F. A., and Ullah M., “S3AM: A spectral-similarity-based spatial attention module for hyperspectral image classification,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 15, pp. 5984-5998, 2022.
[13]
W. Li, H. Chen, Q. Liu, “Attention mechanism and depthwise separable convolution aided 3DCNN for hyperspectral remote sensing image classification,” Remote Sensing, vol. 14, no. 9, pp. 2215, 2022.
[14]
T. Li, J. Zhang, Y. Zhang, “Classification of hyperspectral image based on deep belief networks,” Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP), 2014.
[15]
R. Zhang, J. Sun, K. Jiang, “Spatial sequential recurrent neural network for hyperspectral image classification,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, vol. 11, no. 11, pp. 4141-4155.
[16]
W. Li, C. Chen, M. Zhang, H. Li, Q. Du, “Data augmentation for hyperspectral image classification with deep CNN,” IEEE Geosci Remote Sens Lett., vol. 16, no. 4, pp. 593–597, 2018.
[17]
X. Li, Z. Sun, J. Xue, Z. Ma, “A concise review of recent few-shot meta-learning methods. Neurocomputing,” vol. 456, pp. 463–468, 2021.
[18]
B. Liu, X. Yu, A. Yu, P. Zhang, G. Wan, R. Wang, “Deep few-shot learning for hyperspectral image classification,” IEEE Trans Geosci Remote Sens., vol. 57, no. 4, pp. 2290–2304, 2019.
[19]
W. Li, C. Chen, M. Zhang, H. Li, Q. Du, “Data augmentation for hyperspectral image classification with deep CNN,” IEEE Geosci Remote Sens Lett, 2018, vol. 16, no. 4, pp. 593–597.
[20]
Haut JM, Paoletti ME, J. Plaza, A. Plaza, J. Li, “Hyperspectral image classification using random occlusion data augmentation,” IEEE Geosci Remote Sens Lett. vol. 16, no. 11, pp. 1751–1755.
[21]
X. Li, Z. Sun, J. Xue, Z. Ma, “A concise review of recent few-shot meta-learning methods. Neurocomputing,” vol. 456, pp.463–468, 2021.
[22]
B. Liu, X. Yu, A. Yu, P. Zhang, G. Wan, R. Wang, “Deep few-shot learning for hyperspectral image classification,” IEEE Trans Geosci Remote Sens., vol. 57, no. 4, pp. 2290–2304, 2019.
[23]
T. Chen, S. Kornblith, M. Norouzi, “A simple framework for contrastive learning of visual representations,” International conference on machine learning. PMLR, pp. 1597-1607, 2020.
[24]
S. Zhang, Z. Chen, D. Wang, “Cross-Domain Few-Shot Contrastive Learning for Hyperspectral Images Classification,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022.
[25]
S. Hou, H. Shi, X. Cao, X. Zhang, L. Jiao, “Hyperspectral imagery classification based on contrastive learning”, IEEE Trans Geosci Remote Sens., vol. 60, no. 5521213, 2022.
[26]
L. Song, Z. Feng, S. Yang, X. Zhang, and L. Jiao, “Self-supervisedassisted semi-supervised residual network for hyperspectral image classification,” Remote Sens., vol. 14, no. 13, p. 2997, Jun. 2022.
[27]
Hyperspectral Remote Sensing Scenes - Grupo de Inteligencia Computacional (GIC), http://www.ehu.eus/ccwintco/index.php?title$=$Hyperspectral_Remote_Sensing_Scenes, accessed on 2023-04-19.
[28]
S. Jiang, S. Jia. “A 3D lightweight Siamese network for hyperspectral image classification with limited samples. ICCPR 2021. Proceedings of the 10th International Conference on Computing and Pattern Recognition, pp. 142–148, 2021.
[29]
L. Zhao, W. Luo, Q. Liao Q, S. Chen, J. Wu, “Hyperspectral image classification with contrastive self-supervised learning under limited labeled samples,” IEEE Geosci Remote Sens Lett., vol. 19, no. 6008205, 2022.
[30]
Q. Liu, J. Peng, G. Zhang, “Deep contrastive learning network for small-sample hyperspectral image classification,” Journal of Remote Sensing, 2023, vol. 3, no. 0025.

Cited By

View all

Index Terms

  1. Self-Supervised Contrastive Learning Residual Network for Hyperspectral Image Classification Under Limited Labeled Samples

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICIGP '24: Proceedings of the 2024 7th International Conference on Image and Graphics Processing
    January 2024
    480 pages
    ISBN:9798400716720
    DOI:10.1145/3647649
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 03 May 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. contrastive learning
    2. data augmentation
    3. hyperspectral image classification
    4. residual network
    5. self-supervised learning

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Funding Sources

    • the Hainan Key Research and Development Plan for Scientific and Technological Collaboration Projects

    Conference

    ICIGP 2024

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)17
    • Downloads (Last 6 weeks)3
    Reflects downloads up to 15 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media