no code implementations • 19 Jul 2024 • Rodrigo Kobashikawa Rosa, Danilo Braga, Danilo Silva
Finally, this paper proposes a more realistic dataset division that allows for more diversity in the training dataset while keeping the division free from data leakage.
no code implementations • 17 Apr 2024 • João Gabriel Vinholi, Marco Chini, Anis Amziane, Renato Machado, Danilo Silva, Patrick Matgen
Comparing images captured by disparate sensors is a common challenge in remote sensing.
no code implementations • 16 Feb 2024 • Bruno Laboissiere Camargos Borges, Bruno Machado Pacheco, Danilo Silva
Our findings show that post-hoc confidence estimators offer a cost-effective approach to reducing the impacts of distribution shift.
1 code implementation • 11 Jul 2023 • Bruno Machado Pacheco, Victor Hugo Rocha de Oliveira, Augusto Braga Fernandes Antunes, Saulo Domingos de Souza Pedro, Danilo Silva
Brain age prediction using neuroimaging data has shown great potential as an indicator of overall brain health and successful aging, as well as a disease biomarker.
1 code implementation • 24 May 2023 • Luís Felipe P. Cattelan, Danilo Silva
Our results show that a simple $p$-norm normalization of the logits, followed by taking the maximum logit as the confidence estimator, can lead to considerable gains in selective classification performance, completely fixing the pathological behavior observed in many classifiers.
1 code implementation • 14 Dec 2022 • Bruno Machado Pacheco, Guilherme de Souza e Cassia, Danilo Silva
Our experiments show that the choice of a BE method can compromise up to 15. 7% of the tumor segmentation performance.
no code implementations • 23 Dec 2021 • Victor H. R. Oliveira, Augusto Antunes, Alexandre S. Soares, Arthur D. Reys, Robson Z. Júnior, Saulo D. S. Pedro, Danilo Silva
In this work, deep learning techniques for brain age prediction from magnetic resonance images are investigated, aiming to assist in the identification of biomarkers of the natural aging process.
1 code implementation • 29 Jul 2020 • Arthur D. Reys, Danilo Silva, Daniel Severo, Saulo Pedro, Marcia M. de Souza e Sá, Guilherme A. C. Salgado
ICD coding from electronic clinical records is a manual, time-consuming and expensive process.