1 code implementation • 22 Dec 2023 • Iris Dominguez-Catena, Daniel Paternain, Mikel Galar
Often, these biases can be traced back to the data used for training, where large uncurated datasets have become the norm.
1 code implementation • 28 Mar 2023 • Iris Dominguez-Catena, Daniel Paternain, Mikel Galar
One of the most prominent types of demographic bias are statistical imbalances in the representation of demographic groups in the datasets.
no code implementations • 8 Mar 2023 • Marco D'Alessandro, Alberto Alonso, Enrique Calabrés, Mikel Galar
Few-Shot Class Incremental Learning (FSCIL) is a challenging continual learning task, where limited training examples are available during several learning sessions.
no code implementations • 11 Oct 2022 • Iris Dominguez-Catena, Daniel Paternain, Mikel Galar
Our findings support the need for a thorough bias analysis of public datasets in problems like FER, where a global balance of demographic representation can still hide other types of bias that harm certain demographic groups.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 28 Jul 2022 • Francesco Zola, Jose Alvaro Fernandez-Carrasco, Jan Lukas Bruse, Mikel Galar, Zeno Geradts
Biometric systems represent valid solutions in tasks like user authentication and verification, since they are able to analyze physical and behavioural features with high precision.
1 code implementation • 20 May 2022 • Iris Dominguez-Catena, Daniel Paternain, Mikel Galar
Of the three metrics proposed, two focus on the representational and stereotypical bias of the dataset, and the third one on the residual bias of the trained model.
Facial Expression Recognition Facial Expression Recognition (FER) +1
no code implementations • 27 May 2020 • Francesco Zola, Jan Lukas Bruse, Xabier Etxeberria Barrio, Mikel Galar, Raul Orduna Urrutia
In fact, setting GAN training parameters is non-trivial and heavily affects the quality of the generated synthetic data.
no code implementations • 8 Mar 2019 • Mikel Elkano, Humberto Bustince, Mikel Galar
Our findings show that, although slightly inferior, Big Data classifiers are gradually catching up with state-of-the-art classifiers for Small data, suggesting that a unified learning algorithm for Big and Small Data might be possible.
no code implementations • 28 Feb 2019 • Mikel Elkano, Mikel Uriz, Humberto Bustince, Mikel Galar
We present a new distributed fuzzy partitioning method to reduce the complexity of multi-way fuzzy decision trees in Big Data classification problems.
1 code implementation • 25 Feb 2019 • Mikel Elkano, Jose Sanz, Edurne Barrenechea, Humberto Bustince, Mikel Galar
However, when it comes to Big Data classification problems, fuzzy rule-based classifiers have not been able to maintain the good trade-off between accuracy and interpretability that has characterized these techniques in non-Big Data environments.