Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. Recently proposed evidential neural networks explicitly account for different uncertainties by treating the network's outputs as evidence to parameterize the Dirichlet distribution, and achieve impressive performance in uncertainty estimation. However, for high data uncertainty samples but annotated with the one-hot label, the evidence-learning process for those mislabeled classes is over-penalized and remains hindered. To address this problem, we propose a novel method, Fisher Information-based Evidential Deep Learning ($\mathcal{I}$-EDL). In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes. The generalization ability of our network is further improved by optimizing the PAC-Bayesian bound. As demonstrated empirically, our proposed method consistently outperforms traditional EDL-related algorithms in multiple uncertainty estimation tasks, especially in the more challenging few-shot classification settings.

翻译：不确定性估计是使深度学习在实际应用中可靠的关键因素。近期提出的证据神经网络通过将网络输出视为参数化狄利克雷分布的"证据"，明确考虑了不同的不确定性类型，并在不确定性估计任务中取得了显著效果。然而，对于数据不确定性较高但标注为独热标签的样本，其误标签类别的证据学习过程会受到过度惩罚而受阻。为解决此问题，我们提出了一种新方法——基于Fisher信息的证据深度学习（$\mathcal{I}$-EDL）。具体而言，我们引入Fisher信息矩阵（FIM）来度量每个样本所携带证据的信息量，据此动态调整目标损失项的权重，使网络更专注于不确定类别的表示学习。此外，通过优化PAC-Bayesian界进一步提升了网络的泛化能力。实验证明，我们的方法在多项不确定性估计任务中（尤其在更具挑战性的少样本分类场景下）始终优于传统EDL相关算法。