collaborators

8 papers

cs.CV2024

Non-Linear Outlier Synthesis for Out-of-Distribution Detection

Lars Doorenbos, Raphael Sznitman, Pablo Márquez-Neila

The reliability of supervised classifiers is severely hampered by their limitations in dealing with unexpected inputs, leading to great interest in out-of-distribution (OOD) detect…

cs.CV2024

Targeted Visual Prompting for Medical Visual Question Answering

Sergio Tascon-Morales, Pablo Márquez-Neila, Raphael Sznitman

With growing interest in recent years, medical visual question answering (Med-VQA) has rapidly evolved, with multimodal large language models (MLLMs) emerging as an alternative to…

cs.CV2024

Learning Non-Linear Invariants for Unsupervised Out-of-Distribution Detection

Lars Doorenbos, Raphael Sznitman, Pablo Márquez-Neila

The inability of deep learning models to handle data drawn from unseen distributions has sparked much interest in unsupervised out-of-distribution (U-OOD) detection, as it is cruci…

astro-ph.GA2024

Galaxy spectroscopy without spectra: Galaxy properties from photometric images with conditional diffusion models

Lars Doorenbos, Eva Sextl, Kevin Heng +6

Modern spectroscopic surveys can only target a small fraction of the vast amount of photometrically cataloged sources in wide-field surveys. Here, we report the development of a ge…

cs.CV2024

Iterative Deployment Exposure for Unsupervised Out-of-Distribution Detection

Lars Doorenbos, Raphael Sznitman, Pablo Márquez-Neila

Deep learning models are vulnerable to performance degradation when encountering out-of-distribution (OOD) images, potentially leading to misdiagnoses and compromised patient care.…

cs.CV2024

Masked Image Modelling for retinal OCT understanding

Theodoros Pissas, Pablo Márquez-Neila, Sebastian Wolf +2

This work explores the effectiveness of masked image modelling for learning representations of retinal OCT images. To this end, we leverage Masked Autoencoders (MAE), a simple and…