Deep learning has shown great promise in diverse areas of computer vision, such as image classification, object detection and semantic segmentation, among many others. However, as it has been repeatedly demonstrated, deep learning methods trained on a dataset do not generalize well to datasets from other domains or even to similar datasets, due to data distribution shifts. In this work, we propose the use of a meta-learning based few-shot learning approach to alleviate these problems. In order to demonstrate its efficacy, we use two datasets of kidney stones samples acquired with different endoscopes and different acquisition conditions. The results show how such methods are indeed capable of handling domainshifts by attaining an accuracy of 74.38% and 88.52% in the 5-way 5-shot and 5-way 20-shot settings respectively. Instead, in the same dataset, traditional Deep Learning (DL) methods attain only an accuracy of 45%.
Cette contribution présente une méthode d'apprentissage profond pour l'extraction et la fusion d'informations d'images acquises sous différents points de vue dans le but de produire des caractéristiques plus discriminantes entre objets. Notre approche a été conc ¸ue pour mimer l'analyse morpho-constitutionnelle utilisée par les urologues pour classer visuellement des fragments de calculs rénaux à partir de leur surface et section. Des stratégies de fusion de caractéristiques profondes ont permis d'améliorer les performances des extracteurs (structures principales des réseaux) à vue unique de plus de 10 % en termes de précision de la classification des calculs rénaux.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.