论文标题
后网络：通过基于密度的伪计数的不确定性估计不确定性估计
Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
论文作者
论文摘要
准确估计核心和认知不确定性对于建立安全可靠的系统至关重要。传统方法（例如辍学和集合方法）通过对不同子模型的抽样概率进行预测来估计不确定性，从而导致推理时不确定性估计缓慢。最近的工作通过直接预测与神经网络的概率预测的直接预测先前分布的参数来解决这一缺点。尽管这种方法表明了准确的不确定性估计，但它需要定义分布数据的任意目标参数，并认为在培训时已经知道了分布（OOD）数据的不切实际假设。 在这项工作中，我们提出了后验网络（Postnet），该网络使用归一化流量来预测任何输入样本的概率上的单个闭合形式后验分布。邮政网所学到的后验分布准确地反映了分布数据和分发数据的不确定性 - 而无需在培训时访问OOD数据。 Postnet在数据集偏移下实现了OOD检测和不确定性校准的最新结果。
Accurate estimation of aleatoric and epistemic uncertainty is crucial to build safe and reliable systems. Traditional approaches, such as dropout and ensemble methods, estimate uncertainty by sampling probability predictions from different submodels, which leads to slow uncertainty estimation at inference time. Recent works address this drawback by directly predicting parameters of prior distributions over the probability predictions with a neural network. While this approach has demonstrated accurate uncertainty estimation, it requires defining arbitrary target parameters for in-distribution data and makes the unrealistic assumption that out-of-distribution (OOD) data is known at training time. In this work we propose the Posterior Network (PostNet), which uses Normalizing Flows to predict an individual closed-form posterior distribution over predicted probabilites for any input sample. The posterior distributions learned by PostNet accurately reflect uncertainty for in- and out-of-distribution data -- without requiring access to OOD data at training time. PostNet achieves state-of-the art results in OOD detection and in uncertainty calibration under dataset shifts.
