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, \textit{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 focus 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保持可靠的关键因素。最近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”，显式地考虑了不同的不确定性，并在不确定性估计中取得了显著性能。然而，对于具有高数据不确定性但标注为独热标签的样本，那些被错误标注类别的证据学习过程会受到过度惩罚且难以推进。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）。具体来说，我们引入Fisher信息矩阵（FIM）来测量每个样本所携带证据的信息量，据此动态重新加权目标损失项，使网络更关注不确定类别的表示学习。通过优化PAC-贝叶斯界，进一步提升了网络的泛化能力。实验表明，我们的方法在多个不确定性估计任务中均稳定优于传统EDL相关算法，尤其在更具挑战性的小样本分类场景中表现突出。