方法对比

	分布外检测	模型校准	不确定性量化
领域	机器学习	机器学习	仿真
方法族	Machine learning	Machine learning	Process / pipeline
起源年份	2017	2017	Seminal modern form: 2002
提出者	Hendrycks & Gimpel	Platt; Guo et al.	Norbert Wiener (polynomial chaos, 1938); extended to Wiener–Askey scheme by Xiu & Karniadakis (2002)
类型	Reliability and safety method for neural networks	Post-hoc probability correction technique	Computational uncertainty analysis framework
开创性文献	Hendrycks, D., & Gimpel, K. (2017). A baseline for detecting misclassified and out-of-distribution examples in neural networks. International Conference on Learning Representations.	Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. International Conference on Machine Learning, 1321–1330.	Xiu, D. & Karniadakis, G.E. (2002). The Wiener-Askey Polynomial Chaos for Stochastic Differential Equations. SIAM Journal on Scientific Computing, 24(2), 619–644.
别名	OOD Detection, Novelty Detection, Open-Set Recognition, Dağılım Dışı Tespit	Classifier Calibration, Probability Calibration, Score Calibration, Model Kalibrasyonu	UQ, polynomial chaos expansion, PCE, Kriging surrogate
相关	3	3	9
摘要	Out-of-Distribution (OOD) detection is a set of techniques that identify when a deployed machine learning model receives inputs that differ significantly from its training data distribution. Introduced as a formal problem by Hendrycks and Gimpel in 2017, these methods enable models to flag unfamiliar inputs rather than silently produce unreliable predictions, making them foundational to trustworthy and safe AI deployment in high-stakes domains.	Model calibration is a post-hoc technique that adjusts the probability outputs of a trained classifier so that predicted confidence scores match empirical outcome frequencies. A classifier is said to be perfectly calibrated if, among all predictions made with confidence p, exactly a fraction p of them are correct. Systematic miscalibration of modern deep neural networks was rigorously documented by Guo et al. (2017), who showed that networks trained with standard cross-entropy loss tend to be overconfident, and proposed temperature scaling as a simple, effective remedy.	Uncertainty Quantification (UQ) is a computational framework for systematically measuring how uncertainty in the inputs of a model propagates into uncertainty in its outputs. Building on Wiener's polynomial chaos theory (1938) and formalised for general stochastic problems by Xiu and Karniadakis (2002), UQ uses two primary strategies: Polynomial Chaos Expansion (PCE), which represents the model output as a series of orthogonal polynomials matched to the input distributions, and Kriging (Gaussian process) surrogates, which replace an expensive simulation with a fast statistical approximation fitted to a small set of carefully chosen runs.