Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classification

TL;DR

This paper introduces a spatial-aware conformal prediction framework for hyperspectral image classification, providing reliable confidence measures and improving prediction set efficiency by leveraging spatial information.

Contribution

It offers a theoretical validation of conformal prediction for HSI and proposes SACP, a novel spatially-aware method to enhance prediction trustworthiness.

Findings

Theoretical proof of conformal prediction validity for HSI.

SACP improves prediction set efficiency by incorporating spatial info.

Empirical results confirm SACP's effectiveness in real datasets.

Abstract

Hyperspectral image (HSI) classification involves assigning unique labels to each pixel to identify various land cover categories. While deep classifiers have achieved high predictive accuracy in this field, they lack the ability to rigorously quantify confidence in their predictions. Quantifying the certainty of model predictions is crucial for the safe usage of predictive models, and this limitation restricts their application in critical contexts where the cost of prediction errors is significant. To support the safe deployment of HSI classifiers, we first provide a theoretical proof establishing the validity of the emerging uncertainty quantification technique, conformal prediction, in the context of HSI classification. We then propose a conformal procedure that equips any trained HSI classifier with trustworthy prediction sets, ensuring that these sets include the true labels with a user-specified probability (e.g., 95\%). Building on this foundation, we introduce Spatial-Aware Conformal Prediction (\texttt{SACP}), a conformal prediction framework specifically designed for HSI data. This method integrates essential spatial information inherent in HSIs by aggregating the non-conformity scores of pixels with high spatial correlation, which effectively enhances the efficiency of prediction sets. Both theoretical and empirical results validate the effectiveness of our proposed approach. The source code is available at \url{https://github.com/J4ckLiu/SACP}.