@InProceedings{Albuquerque:2023:MuImSe,
               author = "Albuquerque, Eliton",
          affiliation = "{Federal University of Rio Grande do Sul}",
                title = "Multispectral Image Segmentation With Dimensionality Reduction 
                         Using Autoencoders",
            booktitle = "Proceedings...",
                 year = "2023",
               editor = "Clua, Esteban Walter Gonzalez and K{\"o}rting, Thales Sehn and 
                         Paulovich, Fernando Vieira and Feris, Rogerio",
         organization = "Conference on Graphics, Patterns and Images, 36. (SIBGRAPI)",
             keywords = "multispectral image processing, semantic segmentation, 
                         dimensionality reduction.",
             abstract = "Autoencoder (AE) implementations through neural networks have 
                         achieved impressive results on dimensionality reduction tasks, 
                         such as multispectral (MS) imagery compression. Dimensionality 
                         reduction algorithms are necessary when dealing with large 
                         multispectral datasets, since the data captured by mul- tiple 
                         levels of narrow spectral wavelengths causes high processing and 
                         storage costs, particularly when such highly dimensional MS data 
                         are used as input to deep learning networks. Traditional data 
                         compression techniques like Principal Component Analysis (PCA) are 
                         popular in remote sensing applications. However, its 
                         implementation on MS data may make the data unusable for computer 
                         vision (CV) tasks such as image segmentation, especially when 
                         applying severe compression. On the other hand, AEs provide great 
                         generalization capabilities over complex data, especially when 
                         combined with other CV pipelines. For the relevant problem of 
                         semantic segmentation, the results are con- siderably degraded 
                         when using dimensionality-reduced images with PCA. When using 
                         vanilla autoencoders trained with the traditional MSE loss, the 
                         segmentation results improve over PCA but are still considerably 
                         behind the one obtained with uncompressed data, which indicates a 
                         potential domain shift. In this work, we show that training an AE 
                         using a combination of the MSE loss and an additional proxy loss 
                         based on a pre- trained segmentation module can significantly 
                         improve the AE restoration process, alleviating the accuracy drop 
                         of semantic segmentation even for strong compression rates. Our 
                         code is available at https://github.com/elitonfilho/pca.",
  conference-location = "Rio Grande, RS",
      conference-year = "Nov. 06-09, 2023",
                  doi = "10.1109/SIBGRAPI59091.2023.10347038",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI59091.2023.10347038",
             language = "en",
                  ibi = "8JMKD3MGPEW34M/49L85TH",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/49L85TH",
           targetfile = "77_nocopyright.pdf",
        urlaccessdate = "2024, Apr. 27"
}