Paoletti, Mercedes EugeniaTao, Xuanwenhan, lirongWu, ZhaoyueMoreno Álvarez, SergioHaut, Juan M.2024-11-192024-11-192022M. E. Paoletti, X. Tao, L. Han, Z. Wu, S. Moreno-Álvarez and J. M. Haut, "Deep Attention-Driven HSI Scene Classification Based on Inverted Dot-Product," IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, 2022, pp. 1380-1383, doi: 10.1109/IGARSS46834.2022.9883028978-1-6654-2792-02153-7003| eISSN: 2153-6996https://doi.org/10.1109/IGARSS46834.2022.9883028https://hdl.handle.net/20.500.14468/24424The registered version of this article, first published in “Institute of Electrical and Electronics Engineers Inc, 2022", is available online at the publisher's website: IEEE, https://doi.org/10.1109/IGARSS46834.2022.9883028 La versión registrada de este artículo, publicado por primera vez en “Institute of Electrical and Electronics Engineers Inc, 2022", está disponible en línea en el sitio web del editor: IEEE, https://doi.org/10.1109/IGARSS46834.2022.9883028Capsule networks have been a breakthrough in the field of automatic image analysis, opening a new frontier in the art for image classification. Nevertheless, these models were initially designed for RGB images and naively applying these techniques to remote sensing hyperspectral images (HSI) may lead to sub-optimal behaviour, blowing up the number of parameters needed to train the model or not correctly modeling the spectral relations between the different layers of the scene. To overcome this drawback, this work implements a new capsule-based architecture with attention mechanism to improve the HSI data processing. The attention mechanism is applied during the concurrent iterative routing procedure through an inverted dot-product attentioneninfo:eu-repo/semantics/restrictedAccess12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informáticaactas de congresoArtComputational modelingComputer architectureRoutingData processingIterative methodsImage classification