Out-of-distribution detection in satellite image classification

TL;DR

This paper introduces a Dirichlet Prior Network approach to detect out-of-distribution examples in satellite image classification, addressing distributional shifts and unseen classes to improve model reliability.

Contribution

It applies a Dirichlet Prior Network to quantify uncertainty in satellite image classification, enhancing OOD detection capabilities in remote sensing applications.

Findings

Effective OOD detection in satellite images

Improved identification of unseen classes

Robustness to distributional shifts

Abstract

In satellite image analysis, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data and differences in the geographic area. Deep learning based models may behave in unexpected manner when subjected to test data that has such distributional shifts from the training data, also called out-of-distribution (OOD) examples. Predictive uncertainly analysis is an emerging research topic which has not been explored much in context of satellite image analysis. Towards this, we adopt a Dirichlet Prior Network based model to quantify distributional uncertainty of deep learning models for remote sensing. The approach seeks to maximize the representation gap between the in-domain and OOD examples for a better identification of unknown examples at test time. Experimental results on three exemplary test scenarios show the efficacy of the model in satellite image analysis.