小数据下用贝叶斯神经网络提升异常检测可靠性
Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifiers
- 基于后验对数几率向量设计新型贝叶斯异常评分方法
- 在5000样本以内小数据集上，贝叶斯方法优于确定性方法
- 适合数据稀缺场景的AI安全检测，如医疗诊断
异常检测对人工智能的可靠性和安全性至关重要，但在许多实际场景中，可用训练数据极为有限。贝叶斯神经网络（BNNs）是一类有前景的模型，因其能显式表示认知不确定性（即模型不确定性）。在小样本训练条件下，BNNs尤为适用，因其可融合先验模型信息。本文提出一类基于期望对数几率向量的新贝叶斯后处理异常检测得分，并对比了5种贝叶斯与4种确定性后处理异常检测得分。在包含5000个训练样本或更少的MNIST和CIFAR-10内部分布上的实验表明，贝叶斯方法优于对应确定性方法。
原文摘要 · Abstract (English)
Out-of-Distribution (OOD) detection is critical to AI reliability and safety, yet in many practical settings, only a limited amount of training data is available. Bayesian Neural Networks (BNNs) are a promising class of model on which to base OOD detection, because they explicitly represent epistemic (i.e. model) uncertainty. In the small training data regime, BNNs are especially valuable because they can incorporate prior model information. We introduce a new family of Bayesian posthoc OOD scores based on expected logit vectors, and compare 5 Bayesian and 4 deterministic posthoc OOD scores. Experiments on MNIST and CIFAR-10 In-Distributions, with 5000 training samples or less, show that the Bayesian methods outperform corresponding deterministic methods.
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。