Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels

Matthieu Molinier (Corresponding author), Jorma Kilpi

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    Abstract

    Spatial-spectral approaches applied on hyperspectral images (HSI) with limited labels suffer from overfitting when the size of input filters and the percentage of training data increases. In those cases, pixel values corresponding to testing sets are partly or completely seen during training phase, reducing the number independent testing pixels and leading to overoptimistic accuracy assessment. These effects have been demonstrated in several previous works but still require attention. In this work we propose additional visulizations and measures of the overlapping and overfitting effects, demonstrated on common HSI datasets, to increase awareness on these issues.
    Original languageEnglish
    Title of host publicationProceedings of IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium
    PublisherIEEE Institute of Electrical and Electronic Engineers
    Pages5049-5052
    Number of pages4
    ISBN (Electronic)978-1-5386-9154-0
    ISBN (Print)978-1-5386-9155-7
    DOIs
    Publication statusPublished - 14 Nov 2019
    MoE publication typeA4 Article in a conference publication
    EventIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan
    Duration: 28 Jul 20192 Aug 2019
    https://igarss2019.org

    Conference

    ConferenceIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
    CountryJapan
    CityYokohama
    Period28/07/192/08/19
    Internet address

    Fingerprint

    Labels
    Pixels
    Testing
    Deep learning

    Keywords

    • Deep Learning
    • Remote sensing
    • Hyperspectral imagery
    • limited training samples
    • overfitting

    Cite this

    Molinier, M., & Kilpi, J. (2019). Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels. In Proceedings of IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium (pp. 5049-5052). IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/IGARSS.2019.8900328
    Molinier, Matthieu ; Kilpi, Jorma. / Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels. Proceedings of IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE Institute of Electrical and Electronic Engineers , 2019. pp. 5049-5052
    @inproceedings{3b6dca708ce94ab3a179e49d11494b17,
    title = "Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels",
    abstract = "Spatial-spectral approaches applied on hyperspectral images (HSI) with limited labels suffer from overfitting when the size of input filters and the percentage of training data increases. In those cases, pixel values corresponding to testing sets are partly or completely seen during training phase, reducing the number independent testing pixels and leading to overoptimistic accuracy assessment. These effects have been demonstrated in several previous works but still require attention. In this work we propose additional visulizations and measures of the overlapping and overfitting effects, demonstrated on common HSI datasets, to increase awareness on these issues.",
    keywords = "Deep Learning, Remote sensing, Hyperspectral imagery, limited training samples, overfitting",
    author = "Matthieu Molinier and Jorma Kilpi",
    year = "2019",
    month = "11",
    day = "14",
    doi = "10.1109/IGARSS.2019.8900328",
    language = "English",
    isbn = "978-1-5386-9155-7",
    pages = "5049--5052",
    booktitle = "Proceedings of IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium",
    publisher = "IEEE Institute of Electrical and Electronic Engineers",
    address = "United States",

    }

    Molinier, M & Kilpi, J 2019, Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels. in Proceedings of IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE Institute of Electrical and Electronic Engineers , pp. 5049-5052, IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 28/07/19. https://doi.org/10.1109/IGARSS.2019.8900328

    Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels. / Molinier, Matthieu (Corresponding author); Kilpi, Jorma.

    Proceedings of IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE Institute of Electrical and Electronic Engineers , 2019. p. 5049-5052.

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    TY - GEN

    T1 - Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels

    AU - Molinier, Matthieu

    AU - Kilpi, Jorma

    PY - 2019/11/14

    Y1 - 2019/11/14

    N2 - Spatial-spectral approaches applied on hyperspectral images (HSI) with limited labels suffer from overfitting when the size of input filters and the percentage of training data increases. In those cases, pixel values corresponding to testing sets are partly or completely seen during training phase, reducing the number independent testing pixels and leading to overoptimistic accuracy assessment. These effects have been demonstrated in several previous works but still require attention. In this work we propose additional visulizations and measures of the overlapping and overfitting effects, demonstrated on common HSI datasets, to increase awareness on these issues.

    AB - Spatial-spectral approaches applied on hyperspectral images (HSI) with limited labels suffer from overfitting when the size of input filters and the percentage of training data increases. In those cases, pixel values corresponding to testing sets are partly or completely seen during training phase, reducing the number independent testing pixels and leading to overoptimistic accuracy assessment. These effects have been demonstrated in several previous works but still require attention. In this work we propose additional visulizations and measures of the overlapping and overfitting effects, demonstrated on common HSI datasets, to increase awareness on these issues.

    KW - Deep Learning

    KW - Remote sensing

    KW - Hyperspectral imagery

    KW - limited training samples

    KW - overfitting

    U2 - 10.1109/IGARSS.2019.8900328

    DO - 10.1109/IGARSS.2019.8900328

    M3 - Conference article in proceedings

    SN - 978-1-5386-9155-7

    SP - 5049

    EP - 5052

    BT - Proceedings of IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

    PB - IEEE Institute of Electrical and Electronic Engineers

    ER -

    Molinier M, Kilpi J. Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels. In Proceedings of IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE Institute of Electrical and Electronic Engineers . 2019. p. 5049-5052 https://doi.org/10.1109/IGARSS.2019.8900328