Search Results for author: Jordi Vitrià

Found 14 papers, 4 papers with code

Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR data

1 code implementation5 Sep 2023 Mariona Carós, Ariadna Just, Santi Seguí, Jordi Vitrià

Airborne LiDAR systems have the capability to capture the Earth's surface by generating extensive point cloud data comprised of points mainly defined by 3D coordinates.

Scene Segmentation Unsupervised Pre-training

Time-based Self-supervised Learning for Wireless Capsule Endoscopy

no code implementations20 Apr 2022 Guillem Pascual, Pablo Laiz, Albert García, Hagen Wenzek, Jordi Vitrià, Santi Seguí

State-of-the-art machine learning models, and especially deep learning ones, are significantly data-hungry; they require vast amounts of manually labeled samples to function correctly.

Self-Supervised Learning

Deep Non-Crossing Quantiles through the Partial Derivative

no code implementations30 Jan 2022 Axel Brando, Joan Gimeno, Jose A. Rodríguez-Serrano, Jordi Vitrià

Quantile Regression (QR) provides a way to approximate a single conditional quantile.

Algorithmic Causal Effect Identification with causaleffect

1 code implementation9 Jul 2021 Martí Pedemonte, Jordi Vitrià, Álvaro Parafita

Our evolution as a species made a huge step forward when we understood the relationships between causes and effects.

Causal Inference

Graph Convolutional Embeddings for Recommender Systems

no code implementations5 Mar 2021 Paula Gómez Duran, Alexandros Karatzoglou, Jordi Vitrià, Xin Xin, Ioannis Arapakis

In this work, we generalize the use of GCNs for N-partite graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures.

Collaborative Filtering Recommendation Systems

Causal Inference with Deep Causal Graphs

no code implementations15 Jun 2020 Álvaro Parafita, Jordi Vitrià

Parametric causal modelling techniques rarely provide functionality for counterfactual estimation, often at the expense of modelling complexity.

Causal Inference Fairness

WCE Polyp Detection with Triplet based Embeddings

no code implementations10 Dec 2019 Pablo Laiz, Jordi Vitrià, Hagen Wenzek, Carolina Malagelada, Fernando Azpiroz, Santi Seguí

Automatic image analysis methods can be used to reduce the time needed for physicians to evaluate a capsule endoscopy video, however these methods are still in a research phase.

Medical Procedure Metric Learning

Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians

1 code implementation NeurIPS 2019 Axel Brando, Jose A. Rodríguez-Serrano, Jordi Vitrià, Alberto Rubio

In this paper, we propose a generic deep learning framework that learns an Uncountable Mixture of Asymmetric Laplacians (UMAL), which will allow us to estimate heterogeneous distributions of the output variable and shows its connections to quantile regression.

Decision Making regression

Explaining Visual Models by Causal Attribution

no code implementations19 Sep 2019 Álvaro Parafita, Jordi Vitrià

Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest.

Uncertainty Modelling in Deep Networks: Forecasting Short and Noisy Series

no code implementations24 Jul 2018 Axel Brando, Jose A. Rodríguez-Serrano, Mauricio Ciprian, Roberto Maestre, Jordi Vitrià

Deep Learning is a consolidated, state-of-the-art Machine Learning tool to fit a function when provided with large data sets of examples.

Uncertainty Gated Network for Land Cover Segmentation

no code implementations29 May 2018 Guillem Pascual, Santi Seguí, Jordi Vitrià

The production of thematic maps depicting land cover is one of the most common applications of remote sensing.

General Classification Semantic Segmentation

Generic Feature Learning for Wireless Capsule Endoscopy Analysis

no code implementations26 Jul 2016 Santi Seguí, Michal Drozdzal, Guillem Pascual, Petia Radeva, Carolina Malagelada, Fernando Azpiroz, Jordi Vitrià

Most of the CAD systems in the capsule endoscopy share a common system design, but use very different image and video representations.

Learning to count with deep object features

1 code implementation29 May 2015 Santi Seguí, Oriol Pujol, Jordi Vitrià

Learning to count is a learning strategy that has been recently proposed in the literature for dealing with problems where estimating the number of object instances in a scene is the final objective.

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