Toward a Trustworthy Classifier With Deep CNN: Uncertainty Estimation Meets Hyperspectral Image

Recently, deep convolutional neural networks (CNNs) have achieved a high classification accuracy of hyperspectral images (HSIs). However, high accuracy is not the only goal of a good HSI classifier. In real-world applications, it is necessary to tell whether the classifier is certain about its classification result, which is critical for safe usage. Unfortunately, most of the existing models do not consider the issue. In this study, uncertainty is estimated and reduced to build a trustworthy HSI classifier. First, since the output probabilities of the softmax layer cannot represent the confidence scores, the distance measurement scheme is used to measure the confidence scores. Then, a trustworthy HSI classifier, which reduces the predictive uncertainty in CNN (i.e., PU-CNN), is obtained by minimizing the distance to the correct centroid. Second, the fact that a training sample of HSI usually contains many pixel vectors that belong to different classes brings label uncertainty. Then, label uncertainty CNN (i.e., LU-CNN), which uses a classifier-consistent estimator to recover the multiple classes in each HSI sample, is proposed. LU-CNN computes loss over candidate label sets to find the optimal classes, which leads to a trustworthy HSI classifier. Finally, the combination of PU-CNN and LU-CNN [i.e., predictive uncertainty and label uncertainty (PL-CNN)] is proposed to address predictive uncertainty and label uncertainty at the same time. Experimental results on the three popular hyperspectral datasets show that the proposed methods yield improvements in both accuracy and confidence. The proposed trustworthy classifier opens a new window for the safe usage of HSI.