Výsledky vyhledávání - "Navarini Alexander"

Akademický článek

Toward photothermal damage detection during laser osteotomy using optical coherence tomography

Autor: Grava Aikaterina, Hamidi Arsham, Gonzalez-Jimenez Alvaro, Bayhaqi Yakub A., Navarini Alexander A., Cattin Philippe C., Canbaz Ferda

Publikováno v: EPJ Web of Conferences, Vol 287, p 09029 (2023)

Feedback systems have been utilized to reduce the possible thermal side effects of lasers for surgery by means of temperature monitoring to control irrigation systems. In this study, we investigated the potential application of optical coherence tomo

Externí odkaz: https://doaj.org/article/661824b27fdc48b7a886def3389d20a6

Zobrazit plný text záznamu

Report

Hyperbolic Metric Learning for Visual Outlier Detection

Autor: Gonzalez-Jimenez, Alvaro, Lionetti, Simone, Bazazian, Dena, Gottfrois, Philippe, Gröger, Fabian, Pouly, Marc, Navarini, Alexander

Out-Of-Distribution (OOD) detection is critical to deploy deep learning models in safety-critical applications. However, the inherent hierarchical concept structure of visual data, which is instrumental to OOD detection, is often poorly captured by c

Externí odkaz: http://arxiv.org/abs/2403.15260

Zobrazit plný text záznamu

Report

Towards Reliable Dermatology Evaluation Benchmarks

Autor: Gröger, Fabian, Lionetti, Simone, Gottfrois, Philippe, Gonzalez-Jimenez, Alvaro, Groh, Matthew, Daneshjou, Roxana, Consortium, Labelling, Navarini, Alexander A., Pouly, Marc

Publikováno v: Proceedings of the 3rd Machine Learning for Health Symposium, PMLR 225:101-128, 2023

Benchmark datasets for digital dermatology unwittingly contain inaccuracies that reduce trust in model performance estimates. We propose a resource-efficient data-cleaning protocol to identify issues that escaped previous curation. The protocol lever

Externí odkaz: http://arxiv.org/abs/2309.06961

Zobrazit plný text záznamu

Report

Robust T-Loss for Medical Image Segmentation

Autor: Gonzalez-Jimenez, Alvaro, Lionetti, Simone, Gottfrois, Philippe, Gröger, Fabian, Pouly, Marc, Navarini, Alexander

This paper presents a new robust loss function, the T-Loss, for medical image segmentation. The proposed loss is based on the negative log-likelihood of the Student-t distribution and can effectively handle outliers in the data by controlling its sen

Externí odkaz: http://arxiv.org/abs/2306.00753

Zobrazit plný text záznamu

Report

SelfClean: A Self-Supervised Data Cleaning Strategy

Autor: Gröger, Fabian, Lionetti, Simone, Gottfrois, Philippe, Gonzalez-Jimenez, Alvaro, Amruthalingam, Ludovic, Consortium, Labelling, Groh, Matthew, Navarini, Alexander A., Pouly, Marc

Most benchmark datasets for computer vision contain irrelevant images, near duplicates, and label errors. Consequently, model performance on these benchmarks may not be an accurate estimate of generalization capabilities. This is a particularly acute

Externí odkaz: http://arxiv.org/abs/2305.17048

Zobrazit plný text záznamu