no code implementations • 2 Apr 2024 • Carlos Plou, Nerea Gallego, Alberto Sabater, Eduardo Montijano, Pablo Urcola, Luis Montesano, Ruben Martinez-Cantin, Ana C. Murillo
Our novel pipeline is able to achieve high accuracy under these challenging conditions and incorporates a Bayesian approach (Laplace ensembles) to increase the robustness in the predictions, which is fundamental for medical applications.
no code implementations • 2 Apr 2024 • Carlos Plou, Ana C. Murillo, Ruben Martinez-Cantin
Model-based RL, by building a dynamic model of the robot, enables data reuse and transfer learning between tasks with the same robot and similar environment.
no code implementations • 8 Feb 2024 • Pedro Osório, Alexandre Bernardino, Ruben Martinez-Cantin, José Santos-Victor
Affordances are fundamental descriptors of relationships between actions, objects and effects.
1 code implementation • ICCV 2023 • Lorenzo Mur-Labadia, Jose J. Guerrero, Ruben Martinez-Cantin
We use this method to build the largest and most complete dataset on affordances based on the EPIC-Kitchen dataset, EPIC-Aff, which provides interaction-grounded, multi-label, metric and spatial affordance annotations.
no code implementations • ICCV 2023 • Javier Rodríguez-Puigvert, Víctor M. Batlle, J. M. M. Montiel, Ruben Martinez-Cantin, Pascal Fua, Juan D. Tardós, Javier Civera
However, there are scenarios, especially in medicine in the case of endoscopies, where such data cannot be obtained.
no code implementations • 2 Mar 2023 • Lorenzo Mur-Labadia, Ruben Martinez-Cantin, Jose J. Guerrero
We present a novel Bayesian deep network to detect affordances in images, at the same time that we quantify the distribution of the aleatoric and epistemic variance at the spatial level.
no code implementations • 20 May 2022 • Melani Sanchez-Garcia, Roberto Morollon-Ruiz, Ruben Martinez-Cantin, Jose J. Guerrero, Eduardo Fernandez-Jover
The development of new artificial vision simulation systems can be useful to guide the development of new visual devices and the optimization of field of view and resolution to provide a helpful and valuable visual aid to profoundly or totally blind patients.
no code implementations • 30 Sep 2021 • Melani Sanchez-Garcia, Alejandro Perez-Yus, Ruben Martinez-Cantin, Jose J. Guerrero
In this work, we propose an augmented reality navigation system for visual prosthesis that incorporates a software of reactive navigation and path planning which guides the subject through convenient, obstacle-free route.
no code implementations • 27 Sep 2021 • Lorenzo Mur-Labadia, Ruben Martinez-Cantin
Our Bayesian model is able to capture both the aleatoric uncertainty from the scene and the epistemic uncertainty associated with the model and previous learning process.
no code implementations • 2 Mar 2020 • Javier Garcia-Barcos, Ruben Martinez-Cantin
First, to deal with input noise and provide a safe and repeatable policy we use an improved version of unscented Bayesian optimization.
no code implementations • 26 Feb 2019 • Javier Garcia-Barcos, Ruben Martinez-Cantin
But, when compared with other acquisition functions in the sequential setting, Thompson sampling is known to perform suboptimally.
no code implementations • 25 Sep 2018 • Melani Sanchez-Garcia, Ruben Martinez-Cantin, Jose J. Guerrero
Most research in simulated prosthetic vision is performed based on static images, while very few researchers have addressed the problem of scene recognition through video sequences.
no code implementations • 12 Dec 2017 • Ruben Martinez-Cantin, Kevin Tee, Michael McCourt
In this paper, we present an empirical evaluation of Bayesian optimization methods in the presence of outliers.
no code implementations • 18 Jul 2017 • Ruben Martinez-Cantin, Michael McCourt, Kevin Tee
Bayesian optimization has recently attracted the attention of the automatic machine learning community for its excellent results in hyperparameter tuning.
no code implementations • 2 Oct 2016 • Ruben Martinez-Cantin
In order to generalize to unknown functions in a black-box fashion, the common assumption is that the underlying function can be modeled with a stationary process.
no code implementations • 7 Mar 2016 • José Nogueira, Ruben Martinez-Cantin, Alexandre Bernardino, Lorenzo Jamone
We address the robot grasp optimization problem of unknown objects considering uncertainty in the input space.
no code implementations • 5 Jun 2015 • Ruben Martinez-Cantin
Bayesian optimization has shown to be a fundamental global optimization algorithm in many applications: ranging from automatic machine learning, robotics, reinforcement learning, experimental design, simulations, etc.
1 code implementation • 29 May 2014 • Ruben Martinez-Cantin
BayesOpt is a library with state-of-the-art Bayesian optimization methods to solve nonlinear optimization, stochastic bandits or sequential experimental design problems.
no code implementations • 3 Sep 2013 • Ruben Martinez-Cantin
On one side, we present a general framework for Bayesian optimization and we compare it with some related fields in active learning and Bayesian numerical analysis.