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

TL;DR

This paper introduces an entropic optimal transport loss function that enhances the robustness of deep neural networks against label noise in remote sensing image classification tasks, improving performance with noisy labels.

Contribution

It proposes a novel entropic optimal transport loss for training deep neural networks that are more resistant to label noise in remote sensing datasets.

Findings

The method is highly tolerant to significant label noise.

It outperforms state-of-the-art methods on remote sensing datasets.

Effective on both scene and pixel-based hyperspectral images.

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.