1 code implementation • 23 Nov 2020 • Carlos H. C. Pena, Mateus G. Machado, Mariana S. Barros, José D. P. Silva, Lucas D. Maciel, Tsang Ing Ren, Edna N. S. Barros, Pedro H. M. Braga, Hansenclever F. Bassani
The IEEE Very Small Size Soccer (VSSS) is a robot soccer competition in which two teams of three small robots play against each other.
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 • 15 May 2020 • Marcel Santana Santos, Tsang Ing Ren, Nima Khademi Kalantari
Since the number of HDR images for training is limited, we propose to train our system in two stages.
Inverse-Tone-Mapping Image and Video Processing Graphics
no code implementations • 18 Jan 2020 • Pedro D. Marrero Fernandez, Tsang Ing Ren, Tsang Ing Jyh, Fidel A. Guerrero Peña, Alexandre Cunha
We propose a deep metric learning model to create embedded sub-spaces with a well defined structure.
no code implementations • 22 Oct 2019 • Fidel A. Guerrero Peña, Pedro D. Marrero Fernandez, Paul T. Tarr, Tsang Ing Ren, Elliot M. Meyerowitz, Alexandre Cunha
We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions.
no code implementations • 28 Aug 2019 • Fidel Alejandro Guerrero Peña, Pedro Diamel Marrero Fernández, Tsang Ing Ren, Germano Crispim Vasconcelos, Alexandre Cunha
Multi-Focus Image Fusion seeks to improve the quality of an acquired burst of images with different focus planes.
no code implementations • 26 Aug 2019 • Fidel A. Guerrero-Peña, Pedro D. Marrero Fernandez, Tsang Ing Ren, Alexandre Cunha
We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images.
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.
1 code implementation • 8 Feb 2019 • Pedro D. Marrero Fernandez, Fidel A. Guerrero Peña, Tsang Ing Ren, Alexandre Cunha
We present a new end-to-end network architecture for facial expression recognition with an attention model.
Facial Expression Recognition Facial Expression Recognition (FER) +1
no code implementations • 28 Nov 2018 • Hector N. B. Pinheiro, Tsang Ing Ren, Stefan Scheib, Armel Rosselet, Stefan Thieme-Marti
We presented a 2D/3D MV image registration method based on a Convolutional Neural Network.
no code implementations • 1 Nov 2018 • Rafael M. O. Cruz, George D. C. Cavalcanti, Tsang Ing Ren
Dynamic classifier selection systems aim to select a group of classifiers that is most adequate for a specific query pattern.
2 code implementations • 29 Oct 2018 • Fidel A. Guerrero Peña, Pedro D. Marrero Fernández, Tsang Ing Ren, Jorge J. G. Leandro, Ricardo Nishihara
The primary motivation is that current bursts deblurring methods do not handle well situations in which misalignment or out-of-context frames are present in the burst.
2 code implementations • 19 Oct 2018 • Pedro D. Marrero Fernandez, Fidel A. Guerrero-Peña, Tsang Ing Ren, Jorge J. G. Leandro
The objective of this work is to propose a new fast and robust method for automatic ColorChecker detection.
no code implementations • 30 Sep 2018 • Rafael M. O. Cruz, Robert Sabourin, George D. C. Cavalcanti, Tsang Ing Ren
The meta-features are extracted from the training data and used to train a meta-classifier to predict whether or not a base classifier is competent enough to classify an input instance.
2 code implementations • 21 Feb 2018 • Fidel A. Guerrero-Pena, Pedro D. Marrero Fernandez, Tsang Ing Ren, Mary Yui, Ellen Rothenberg, Alexandre Cunha
We propose a new multiclass weighted loss function for instance segmentation of cluttered cells.