Search Results for author: Daniel Ramos

Found 8 papers, 2 papers with code

Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks

no code implementations31 Jul 2022 Sergio A. Balanya, Juan Maroñas, Daniel Ramos

We show that when there is plenty of data complex models like neural networks yield better performance, but are prone to fail when the amount of data is limited, a common situation in certain post-hoc calibration applications like medical diagnosis.

Inductive Bias Medical Diagnosis

On Calibration of Mixup Training for Deep Neural Networks

1 code implementation22 Mar 2020 Juan Maroñas, Daniel Ramos, Roberto Paredes

Data Augmentation (DA) strategies have been proposed to regularize these models, being Mixup one of the most popular due to its ability to improve the accuracy, the uncertainty quantification and the calibration of DNN.

Data Augmentation

Bayesian Strategies for Likelihood Ratio Computation in Forensic Voice Comparison with Automatic Systems

no code implementations18 Sep 2019 Daniel Ramos, Juan Maroñas, Alicia Lozano-Diez

This paper explores several strategies for Forensic Voice Comparison (FVC), aimed at improving the performance of the LRs when using generative Gaussian score-to-LR models.

Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks

1 code implementation23 Aug 2019 Juan Maroñas, Roberto Paredes, Daniel Ramos

Deep Neural Networks (DNNs) have achieved state-of-the-art accuracy performance in many tasks.

Image Classification

Generative Models For Deep Learning with Very Scarce Data

no code implementations21 Mar 2019 Juan Maroñas, Roberto Paredes, Daniel Ramos

The goal of this paper is to deal with a data scarcity scenario where deep learning techniques use to fail.

General Classification

Improving Automated Latent Fingerprint Identification using Extended Minutia Types

no code implementations23 Oct 2018 Ram P. Krish, Julian Fierrez, Daniel Ramos, Fernando Alonso-Fernandez, Josef Bigun

We report significant improvements in the rank identification accuracies when these minutiae matchers are augmented with our proposed algorithm based on rare minutiae features.

Offline Deep models calibration with bayesian neural networks

no code implementations27 Sep 2018 Juan Maroñas, Roberto Paredes, Daniel Ramos

We apply Bayesian Neural Networks to improve calibration of state-of-the-art deep neural networks.

Cannot find the paper you are looking for? You can Submit a new open access paper.