no code implementations • PROPOR 2022 2022 • Hidelberg O. Albuquerque, Rosimeire Costa, Gabriel Silvestre, Ellen Souza, Nádia F. F. da Silva, Douglas Vitório, Gyovana Moriyama, Lucas Martins, Luiza Soezima, Augusto Nunes, Felipe Siqueira, João P. Tarrega, Joao V. Beinotti, Marcio Dias, Matheus Silva, Miguel Gardini, Vinicius Silva, André C. P. L. F. de Carvalho, Adriano L. I. Oliveira
The amount of legislative documents produced within the past decade has risen dramatically, making it difficult for law practitioners to consult and update legislation.
no code implementations • 19 Oct 2020 • Victor L. F. Souza, Adriano L. I. Oliveira, Rafael M. O. Cruz, Robert Sabourin
We proposed a method based on a global validation strategy with an external archive to control overfitting during the search for the most discriminant representation.
1 code implementation • 16 Aug 2020 • Angel Ayala, Bruno Fernandes, Francisco Cruz, David Macêdo, Adriano L. I. Oliveira, Cleber Zanchettin
The experiments show that our model keeps high accuracy while substantially reducing the number of parameters and flops.
2 code implementations • 7 Jun 2020 • David Macêdo, Tsang Ing Ren, Cleber Zanchettin, Adriano L. I. Oliveira, Teresa Ludermir
In this paper, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to produce low entropy probability distributions in disagreement with the principle of maximum entropy.
no code implementations • 7 Apr 2020 • Victor L. F. Souza, Adriano L. I. Oliveira, Rafael M. O. Cruz, Robert Sabourin
This paper investigates the presence of overfitting when using Binary Particle Swarm Optimization (BPSO) to perform the feature selection in a context of Handwritten Signature Verification (HSV).
no code implementations • 3 Apr 2020 • Victor L. F. Souza, Adriano L. I. Oliveira, Rafael M. O. Cruz, Robert Sabourin
Among the advantages of this framework is its scalability to deal with some of these challenges and its ease in managing new writers, and hence of being used in a transfer learning context.
2 code implementations • 30 Mar 2020 • Heitor Felix, Walber M. Rodrigues, David Macêdo, Francisco Simões, Adriano L. I. Oliveira, Veronica Teichrieb, Cleber Zanchettin
We used the LINEMOD dataset to evaluate the proposed method, and the experimental results show that the proposed method reduces the memory requirement by almost 99\% in comparison to the original architecture with the cost of reducing half the accuracy in one of the metrics.
1 code implementation • 15 Aug 2019 • David Macêdo, Tsang Ing Ren, Cleber Zanchettin, Adriano L. I. Oliveira, Teresa Ludermir
Consequently, we propose IsoMax, a loss that is isotropic (distance-based) and produces high entropy (low confidence) posterior probability distributions despite still relying on cross-entropy minimization.
no code implementations • 26 Jul 2018 • Victor L. F. Souza, Adriano L. I. Oliveira, Robert Sabourin
The use of features extracted using a deep convolutional neural network (CNN) combined with a writer-dependent (WD) SVM classifier resulted in significant improvement in performance of handwritten signature verification (HSV) when compared to the previous state-of-the-art methods.
no code implementations • ICLR 2018 • David Macêdo, Cleber Zanchettin, Adriano L. I. Oliveira, Teresa Ludermir
Besides, statistical significant performance assessments (p<0. 05) showed DReLU enhanced the test accuracy presented by ReLU in all scenarios.