An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images

Bharath Bhushan Damodaran 1 Rémi Flamary 2 Viven Seguy Nicolas Courty 3
1 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
3 SEASIDE - SEarch, Analyze, Synthesize and Interact with Data Ecosystems
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, UBS - Université de Bretagne Sud
Abstract : 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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02174320
Contributor : Nicolas Courty <>
Submitted on : Friday, July 5, 2019 - 9:15:48 AM
Last modification on : Sunday, July 7, 2019 - 1:34:03 AM

Links full text

Identifiers

Citation

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. 2019. ⟨hal-02174320⟩

Share

Metrics

Record views

14