Saadaoui, H.;                     Farah, S.;                     Lechgar, H.;                     Ghennioui, A.;                     Rhinane, H.    
        Advancing Urban Roof Segmentation: Transformative Deep Learning Models from CNNs to Transformers for Scalable and Accurate Urban Imaging Solutions—A Case Study in Ben Guerir City, Morocco. Technologies 2025, 13, 452.
    https://doi.org/10.3390/technologies13100452
    AMA Style
    
                                Saadaoui H,                                 Farah S,                                 Lechgar H,                                 Ghennioui A,                                 Rhinane H.        
                Advancing Urban Roof Segmentation: Transformative Deep Learning Models from CNNs to Transformers for Scalable and Accurate Urban Imaging Solutions—A Case Study in Ben Guerir City, Morocco. Technologies. 2025; 13(10):452.
        https://doi.org/10.3390/technologies13100452
    
    Chicago/Turabian Style
    
                                Saadaoui, Hachem,                                 Saad Farah,                                 Hatim Lechgar,                                 Abdellatif Ghennioui,                                 and Hassan Rhinane.        
                2025. "Advancing Urban Roof Segmentation: Transformative Deep Learning Models from CNNs to Transformers for Scalable and Accurate Urban Imaging Solutions—A Case Study in Ben Guerir City, Morocco" Technologies 13, no. 10: 452.
        https://doi.org/10.3390/technologies13100452
    
    APA Style
    
                                Saadaoui, H.,                                 Farah, S.,                                 Lechgar, H.,                                 Ghennioui, A.,                                 & Rhinane, H.        
        
        (2025). Advancing Urban Roof Segmentation: Transformative Deep Learning Models from CNNs to Transformers for Scalable and Accurate Urban Imaging Solutions—A Case Study in Ben Guerir City, Morocco. Technologies, 13(10), 452.
        https://doi.org/10.3390/technologies13100452