arXiv:2503.22418cs.LGmath.PR2025-03被引 4
提出新方法评估分类器预测可靠性，尤其适合小样本和分布偏移场景。
Robustness quantification: a new method for assessing the reliability of the predictions of a classifier
- 基于模糊概率思想，量化预测的鲁棒性而非传统不确定性
- 在小样本且分布偏移的数据上仍保持良好性能
- 适合对预测可信度敏感的应用，如医疗、自动驾驶
基于模糊概率领域的现有思想，我们提出一种新方法来评估生成型概率分类器个体预测的可靠性。该方法称为鲁棒性量化，与不确定性量化进行对比，并证明其在从分布偏移的小训练集学习的分类器上依然表现良好。
原文摘要 · Abstract (English)
Based on existing ideas in the field of imprecise probabilities, we present a new approach for assessing the reliability of the individual predictions of a generative probabilistic classifier. We call this approach robustness quantification, compare it to uncertainty quantification, and demonstrate that it continues to work well even for classifiers that are learned from small training sets that are sampled from a shifted distribution.
鲁棒性评估概率分类小样本
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。