@InProceedings{PontiSantRibeCava:2021:AvPiGo,
               author = "Ponti, Moacir Antonelli and Santos, Fernando Pereira dos and 
                         Ribeiro, Leo Sampaio Ferraz and Cavallari, Gabriel Biscaro",
          affiliation = "{Universidade de S{\~a}o Paulo } and {Universidade de S{\~a}o 
                         Paulo } and {Universidade de S{\~a}o Paulo } and {Universidade de 
                         S{\~a}o Paulo}",
                title = "Training Deep Networks from Zero to Hero: avoiding pitfalls and 
                         going beyond",
            booktitle = "Proceedings...",
                 year = "2021",
               editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and 
                         Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario 
                         and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos, 
                         Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira, 
                         Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir 
                         A. and Fernandes, Leandro A. F. and Avila, Sandra",
         organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "Deep Learning, Convolutional Networks, Survey, Training.",
             abstract = "Training deep neural networks may be challenging in real world 
                         data. Using models as black-boxes, even with transfer learning, 
                         can result in poor generalization or inconclusive results when it 
                         comes to small datasets or specific applications. This tutorial 
                         covers the basic steps as well as more recent options to improve 
                         models, in particular, but not restricted to, supervised learning. 
                         It can be particularly useful in datasets that are not as 
                         well-prepared as those in challenges, and also under scarce 
                         annotation and/or small data. We describe basic procedures as data 
                         preparation, optimization and transfer learning, but also recent 
                         architectural choices such as use of transformer modules, 
                         alternative convolutional layers, activation functions, 
                         wide/depth, as well as training procedures including curriculum, 
                         contrastive and self-supervised learning.",
  conference-location = "Gramado, RS, Brazil (virtual)",
      conference-year = "18-22 Oct. 2021",
                  doi = "10.1109/SIBGRAPI54419.2021.00011",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00011",
             language = "en",
                  ibi = "8JMKD3MGPEW34M/45CUTES",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CUTES",
           targetfile = "2021_sibgrapi__tutorial_CR.pdf",
        urlaccessdate = "2024, May 04"
}