69 citations · 318 across the 21 of their papers we have counts for
7 papers · 1 filter
Distinction Maximization Loss: Efficiently Improving Out-of-Distribution Detection and Uncertainty Estimation by Replacing the Loss and Calibrating
David Macêdo, Cleber Zanchettin, Teresa Ludermir
Building robust deterministic neural networks remains a challenge. On the one hand, some approaches improve out-of-distribution detection at the cost of reducing classification acc…
Training Aware Sigmoidal Optimizer
David Macêdo, Pedro Dreyer, Teresa Ludermir +1
Proper optimization of deep neural networks is an open research question since an optimal procedure to change the learning rate throughout training is still unknown. Manually defin…
Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples
David Macêdo, Tsang Ing Ren, Cleber Zanchettin +2
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 pr…
Entropic Out-of-Distribution Detection
David Macêdo, Tsang Ing Ren, Cleber Zanchettin +2
Out-of-distribution (OOD) detection approaches usually present special requirements (e.g., hyperparameter validation, collection of outlier data) and produce side effects (e.g., cl…
Heartbeat Anomaly Detection using Adversarial Oversampling
Jefferson L. P. Lima, David Macêdo, Cleber Zanchettin
Cardiovascular diseases are one of the most common causes of death in the world. Prevention, knowledge of previous cases in the family, and early detection is the best strategy to…
Squeezed Very Deep Convolutional Neural Networks for Text Classification
Andréa B. Duque, Luã Lázaro J. Santos, David Macêdo +1
Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the t…
Spatial-Temporal Graph Convolutional Networks for Sign Language Recognition
Cleison Correia de Amorim, David Macêdo, Cleber Zanchettin
The recognition of sign language is a challenging task with an important role in society to facilitate the communication of deaf persons. We propose a new approach of Spatial-Tempo…