@InProceedings{MagalhãesHira:2023:SpSpCl,
               author = "Magalh{\~a}es, Arthur Teixeira and Hirata, Nina Sumiko Tomita",
          affiliation = "{Instituto de Matem{\'a}tica e Estat{\'{\i}}stica - 
                         Universidade de S{\~a}o Paulo} and {Instituto de Matem{\'a}tica 
                         e Estat{\'{\i}}stica - Universidade de S{\~a}o Paulo}",
                title = "Spider Species Classification Using Vision Transformers and 
                         Convolutional Neural Networks",
            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 = "Machine Learning, Computer Vision, Image Classification, Deep 
                         Learning, Convolutional Neural Networks, Vision Transformers.",
             abstract = "Spiders often seek shelter in the heat and safety of homes and 
                         although most of them are harmless, some can represent a real 
                         danger. Since differentiating spider species can be a challenge 
                         for individuals without prior knowledge, having a method to 
                         identify them could be useful in order to avoid potentially 
                         venomous ones. To address this question, this project aimed to 
                         analyze and compare the performance of convolutional neural 
                         networks (CNN) and vision transformers (ViT) regarding the 
                         quantitative and qualitative performance in the task of 
                         classifying different species of spiders from their images. We 
                         utilized publicly available images consisting of 25 Brazilian 
                         spider species and around 25,000 images. We selected the models 
                         based on their metrics and generalization performance in this 
                         classification task. The preliminary results indicated that 
                         ConvNeXt emerged as the most proficient among the examined 
                         Convolutional Neural Networks, achieving a macro accuracy of 
                         88.5%. As for the Vision Transformers, MaxViT surpassed its 
                         counterparts, registering a macro accuracy of 90.1%, and 
                         outperformed the models in a direct comparison of their 
                         performance metrics. These results may contribute to the 
                         development of applications aimed at identifying spiders and 
                         providing information of interest about the species.",
  conference-location = "Rio Grande, RS",
      conference-year = "Nov. 06-09, 2023",
             language = "en",
                  ibi = "8JMKD3MGPEW34M/4AQHJBE",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/4AQHJBE",
           targetfile = "Spider_Species_Classification.pdf",
        urlaccessdate = "2024, May 01"
}