• Part of
    Ubiquity Network logo
    Interesse beim KIT-Verlag zu publizieren? Informationen für Autorinnen und Autoren

    Lesen sie das Kapitel
  • No readable formats available
  • Semi-supervised methods for CNN based classification of multispectral imagery

    Manuel Bihler, Jiachen Zhou, Michael Heizmann

    Kapitel/Beitrag aus dem Buch: Beyerer, J et al. 2023. OCM 2023 - 6th International Conference on Optical Characterization of Materials, March 22nd – 23rd, 2023, Karlsruhe, Germany : Conference Proceedings.

     Download

    Deep Convolutional neuronal networks, with their recent increase in performance, have become one of the standard techniques for RGB image classification. Due to a lack of large labeled datasets, this is not the case for multispectral image classification. To overcome this, we analyze the use of semisupervised learning for the case of multispectral datasets. We use parameter reduction strategies to create small and efficient multispectral CNNs and combine these computationally efficient classifiers with semi-supervised learning methods. We choose the state-of-the-art semi-supervised methods MixMatch, ReMix- Match, FixMatch, and FlexMatch, to conduct experiments on the multispectral dataset EuroSAT. Additionally, we challenge this semi-supervised multispectral approach with a decreasing number of labeled images. We found that with only 15 labeled images per class, we can reach an accuracy above 80 %. If more labeled images are provided, the analyzed semi-supervised methods can even surpass basic supervised learning strategies.

    :

    Empfohlene Zitierweise für das Kapitel/den Beitrag
    Bihler, M et al. 2023. Semi-supervised methods for CNN based classification of multispectral imagery. In: Beyerer, J et al (eds.), OCM 2023 - 6th International Conference on Optical Characterization of Materials, March 22nd – 23rd, 2023, Karlsruhe, Germany : Conference Proceedings. Karlsruhe: KIT Scientific Publishing. DOI: https://doi.org/10.58895/ksp/1000155014-4
    Lizenz

    This is an Open Access chapter distributed under the terms of the Creative Commons Attribution 4.0 license (unless stated otherwise), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. Copyright is retained by the author(s).

    Peer Review Informationen

    Dieses Buch ist Peer reviewed. Informationen dazu Hier finden Sie mehr Informationen zur wissenschaftlichen Qualitätssicherung der MAP-Publikationen.

    Weitere Informationen

    Veröffentlicht am 25. Mai 2023

    DOI
    https://doi.org/10.58895/ksp/1000155014-4