一个无需重训练的不确定性估计框架，能同时区分模型的两种不确定类型。
CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model
- 通过插入预训练模型任意层，用贝叶斯映射和结构扰动分析联合估计两类不确定性。
- 在分类、回归和分布外检测任务中表现稳定，提供逐层不确定性来源解析。
- 适合高风险场景如医疗诊断，提升模型可解释性与决策可信度。
准确估计深度学习中的不确定性对医疗诊断、自动驾驶等高风险领域至关重要，过度自信的预测可能导致严重后果。理解模型不确定性的来源及其类型，有助于做出风险可控的决策，增强用户信任，并指导数据收集。然而，现有方法大多仅处理单一类型不确定性，或需修改并重新训练基础模型，难以在实际系统中部署。本文提出CUPID（Comprehensive Uncertainty Plug-in estImation moDel），一种通用模块，可在不修改或重训练基础模型的前提下，联合估计偶然性（aleatoric）与认知性（epistemic）不确定性。CUPID可灵活插入任意预训练网络层，通过学习的贝叶斯身份映射建模偶然性不确定性，并利用对结构化扰动的内部响应分析捕捉认知性不确定性。我们在分类、回归及分布外检测等多种任务上评估CUPID，结果表明其性能持续具有竞争力，并提供逐层不确定性来源洞察。通过使不确定性估计模块化、可解释且模型无关，CUPID支持更透明、可信的人工智能系统。相关代码与数据见 https://github.com/a-Fomalhaut-a/CUPID。
原文摘要 · Abstract (English)
Accurate estimation of uncertainty in deep learning is critical for deploying models in high-stakes domains such as medical diagnosis and autonomous decision-making, where overconfident predictions can lead to harmful outcomes. In practice, understanding the reason behind a model's uncertainty and the type of uncertainty it represents can support risk-aware decisions, enhance user trust, and guide additional data collection. However, many existing methods only address a single type of uncertainty or require modifications and retraining of the base model, making them difficult to adopt in real-world systems. We introduce CUPID (Comprehensive Uncertainty Plug-in estImation moDel), a general-purpose module that jointly estimates aleatoric and epistemic uncertainty without modifying or retraining the base model. CUPID can be flexibly inserted into any layer of a pretrained network. It models aleatoric uncertainty through a learned Bayesian identity mapping and captures epistemic uncertainty by analyzing the model's internal responses to structured perturbations. We evaluate CUPID across a range of tasks, including classification, regression, and out-of-distribution detection. The results show that it consistently delivers competitive performance while offering layer-wise insights into the origins of uncertainty. By making uncertainty estimation modular, interpretable, and model-agnostic, CUPID supports more transparent and trustworthy AI. Related code and data are available at https://github.com/a-Fomalhaut-a/CUPID.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。