1 code implementation • 25 Aug 2023 • Lars Doorenbos, Pablo Márquez-Neila, Raphael Sznitman, Pascal Mettes
To make hyperbolic random forests work on multi-class data and imbalanced experiments, we furthermore outline a new method for combining classes based on their lowest common ancestor and a class-balanced version of the large-margin loss.
1 code implementation • 3 Jul 2023 • Sergio Tascon-Morales, Pablo Márquez-Neila, Raphael Sznitman
Our code and data are available at https://github. com/sergiotasconmorales/locvqa.
1 code implementation • 11 Apr 2023 • Alain Jungo, Lars Doorenbos, Tommaso Da Col, Maarten Beelen, Martin Zinkernagel, Pablo Márquez-Neila, Raphael Sznitman
Detecting so-called out-of-distribution (OoD) samples is crucial in safety-critical applications such as robotically guided retinal microsurgery, where distances between the instrument and the retina are derived from sequences of 1D images that are acquired by an instrument-integrated optical coherence tomography (iiOCT) probe.
1 code implementation • CVPR 2023 • Sergio Tascon-Morales, Pablo Márquez-Neila, Raphael Sznitman
Despite considerable recent progress in Visual Question Answering (VQA) models, inconsistent or contradictory answers continue to cast doubt on their true reasoning capabilities.
1 code implementation • ICCV 2023 • Lukas Zbinden, Lars Doorenbos, Theodoros Pissas, Adrian Thomas Huber, Raphael Sznitman, Pablo Márquez-Neila
Semantic segmentation has made significant progress in recent years thanks to deep neural networks, but the common objective of generating a single segmentation output that accurately matches the image's content may not be suitable for safety-critical domains such as medical diagnostics and autonomous driving.
1 code implementation • 23 Aug 2022 • Lars Doorenbos, Olena Torbaniuk, Stefano Cavuoti, Maurizio Paolillo, Giuseppe Longo, Massimo Brescia, Raphael Sznitman, Pablo Márquez-Neila
In this work, we focus on applying our method to the detection of AGN candidates in a Sloan Digital Sky Survey galaxy sample, since the identification and classification of Active Galactic Nuclei (AGN) in the optical band still remains a challenging task in extragalactic astronomy.
1 code implementation • 27 Jun 2022 • Sergio Tascon-Morales, Pablo Márquez-Neila, Raphael Sznitman
Visual Question Answering (VQA) models take an image and a natural-language question as input and infer the answer to the question.
no code implementations • 26 Nov 2021 • Lars Doorenbos, Raphael Sznitman, Pablo Márquez-Neila
Motivated by a simple thought experiment, we propose a characterization of U-OOD based on the invariants of the training dataset.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 31 Mar 2020 • Leonardo Citraro, Pablo Márquez-Neila, Stefano Savarè, Vivek Jayaram, Charles Dubout, Félix Renaut, Andrés Hasfura, Horesh Ben Shitrit, Pascal Fua
Given an image sequence featuring a portion of a sports field filmed by a moving and uncalibrated camera, such as the one of the smartphones, our goal is to compute automatically in real time the focal length and extrinsic camera parameters for each image in the sequence without using a priori knowledges of the position and orientation of the camera.
no code implementations • 16 Jul 2019 • Thomas Kurmann, Pablo Márquez-Neila, Siqing Yu, Marion Munk, Sebastian Wolf, Raphael Sznitman
In this context, we present a method that automatically predicts the presence of biomarkers in OCT cross-sections by incorporating information from the entire volume.
no code implementations • 10 Apr 2019 • Andrea Mendizabal, Pablo Márquez-Neila, Stéphane Cotin
In this paper we present U-Mesh: a data-driven method based on a U-Net architecture that approximates the non-linear relation between a contact force and the displacement field computed by a FEM algorithm.
no code implementations • 2 Feb 2019 • Fayez Lahoud, Radhakrishna Achanta, Pablo Márquez-Neila, Sabine Süsstrunk
To obtain similar binary networks, existing methods rely on the sign activation function.
no code implementations • 7 Jun 2017 • Pablo Márquez-Neila, Mathieu Salzmann, Pascal Fua
Imposing constraints on the output of a Deep Neural Net is one way to improve the quality of its predictions while loosening the requirements for labeled training data.
no code implementations • 27 Nov 2016 • Radhakrishna Achanta, Pablo Márquez-Neila, Pascal Fua, Sabine Süsstrunk
Since information is a natural way of measuring image complexity, our proposed algorithm leads to image segments that are smaller and denser in areas of high complexity and larger in homogeneous regions, thus simplifying the image while preserving its details.
1 code implementation • ICCV 2017 • Bugra Tekin, Pablo Márquez-Neila, Mathieu Salzmann, Pascal Fua
Most recent approaches to monocular 3D human pose estimation rely on Deep Learning.
Ranked #276 on 3D Human Pose Estimation on Human3.6M