An Entropic Optimal Transport loss for learning deep neural networks under label noise in remote sensing images - Observatoire de la Cote d'Azur Accéder directement au contenu
Article Dans Une Revue Computer Vision and Image Understanding Année : 2020

An Entropic Optimal Transport loss for learning deep neural networks under label noise in remote sensing images

Résumé

Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled samples. In practice, collecting large scale accurately labeled datasets is a challenging and tedious task in most scenarios of remote sensing image analysis, thus cheap surrogate procedures are employed to label the dataset. Training deep neural networks on such datasets with inaccurate labels easily overfits to the noisy training labels and degrades the performance of the classification tasks drastically. To mitigate this effect, we propose an original solution with entropic optimal transportation. It allows to learn in an end-to-end fashion deep neural networks that are, to some extent, robust to inaccurately labeled samples. We empirically demonstrate on several remote sensing datasets, where both scene and pixel-based hyperspectral images are considered for classification. Our method proves to be highly tolerant to significant amounts of label noise and achieves favorable results against state-of-the-art methods.
Fichier principal
Vignette du fichier
S1077314219301559.pdf (1.88 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02174320 , version 1 (21-07-2022)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Bharath Bhushan Damodaran, Rémi Flamary, Viven Seguy, Nicolas Courty. An Entropic Optimal Transport loss for learning deep neural networks under label noise in remote sensing images. Computer Vision and Image Understanding, 2020, pp.102863. ⟨10.1016/j.cviu.2019.102863⟩. ⟨hal-02174320⟩
450 Consultations
85 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More