Uncertainty Quantification (UQ) presents a pivotal challenge in the field of Artificial Intelligence (AI), profoundly impacting decision-making, risk assessment and model reliability. In this paper, we introduce Credal and Interval Deep Evidential Classifications (CDEC and IDEC, respectively) as novel approaches to address UQ in classification tasks. CDEC and IDEC leverage a credal set (closed and convex set of probabilities) and an interval of evidential predictive distributions, respectively, allowing us to avoid overfitting to the training data and to systematically assess both epistemic (reducible) and aleatoric (irreducible) uncertainties. When those surpass acceptable thresholds, CDEC and IDEC have the capability to abstain from classification and flag an excess of epistemic or aleatoric uncertainty, as relevant. Conversely, within acceptable uncertainty bounds, CDEC and IDEC provide a collection of labels with robust probabilistic guarantees. CDEC and IDEC are trained using standard backpropagation and a loss function that draws from the theory of evidence. They overcome the shortcomings of previous efforts, and extend the current evidential deep learning literature. Through extensive experiments on MNIST, CIFAR-10 and CIFAR-100, together with their natural OoD shifts (F-MNIST/K-MNIST, SVHN/Intel, TinyImageNet), we show that CDEC and IDEC achieve competitive predictive accuracy, state-of-the-art OoD detection under epistemic and total uncertainty, and tight, well-calibrated prediction regions that expand reliably under distribution shift. An ablation over ensemble size further demonstrates that CDEC attains stable uncertainty estimates with only a small ensemble.
翻译:不确定性量化(UQ)是人工智能(AI)领域的关键挑战,深刻影响决策制定、风险评估与模型可靠性。本文提出信度深度证据分类(CDEC)与区间深度证据分类(IDEC)作为处理分类任务中UQ问题的新方法。CDEC与IDEC分别利用信度集(封闭凸概率集合)与证据预测分布的区间表示,避免对训练数据的过拟合,并系统评估认知(可缩减)与偶然(不可缩减)两类不确定性。当不确定性超过可接受阈值时,CDEC与IDEC能够主动拒绝分类并标记认知或偶然不确定性的超限状态。反之,在可接受不确定性范围内,CDEC与IDEC可提供具有稳健概率保证的标签集合。该方法采用标准反向传播与基于证据理论的损失函数进行训练,克服了先前研究的局限性,拓展了当前证据深度学习的研究范畴。通过在MNIST、CIFAR-10、CIFAR-100及其自然分布偏移数据集(F-MNIST/K-MNIST、SVHN/Intel、TinyImageNet)上的大量实验表明:CDEC与IDEC在保持竞争力的预测准确率的同时,在认知不确定性与总不确定性下的分布外检测达到前沿水平,其预测区域具有紧密且校准良好的特性,并能随分布偏移可靠扩展。集成规模消融实验进一步证明,CDEC仅需小型集成即可获得稳定的不确定性估计。