用于保持准确率的事后不确定性校准的可逆对数变换
Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration
查看机构详情
- University of Pennsylvania（宾夕法尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对现有事后不确定性校准方法的缺陷，提出可逆对数变换InvLT，通过共享标量MLP实现参数不随类别数增长，在保留分类准确率的同时提升校准性能。
中文摘要 AI 辅助
事后校准无需重新训练即可使分类器的预测置信度与其经验准确率对齐。理想的校准器应能纠正非线性校准误差、良好扩展至大标签空间并保留原始预测；现有方法通常至少违反其中一项特性——温度缩放缺乏表达能力，更灵活的参数化替代方案引入随类别数C增长的参数，其他具表达能力的方法无法保留类别分数的排序且可能改变预测类别。我们提出可逆对数变换（InvLT），其将学习到的标量多层感知机（MLP）f: R→R逐元素应用于softmax前的对数。在所有对数维度上共享f使得参数数量与C无关。通过配对逆网络软性鼓励f的单调性（进而保留argmax预测），而非像现有单调校准器那样通过数值积分强制实现；这避免了现有方法的计算开销，且在我们评估的所有设置中均经验性地保留了原始分类准确率。在标准图像分类基准及多种架构上，InvLT在标准校准指标上始终优于大量事后基线方法。
英文摘要
Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining. An ideal calibrator should correct nonlinear miscalibration, scale gracefully to large label spaces, and preserve the original predictions; existing methods typically violate at least one of these properties---temperature scaling lacks expressivity, more flexible parametric alternatives introduce parameters that grow with the number of classes $C$, and other expressive methods do not preserve the rank ordering of class scores and may alter the predicted class. We propose \textbf{Invertible Logits Transformation (InvLT)}, which applies a learned scalar MLP $f:\mathbb{R}\to\mathbb{R}$ element-wise to the pre-softmax logits. Sharing $f$ across all logit dimensions makes the parameter count independent of $C$. Monotonicity of $f$---and hence preservation of the argmax prediction---is softly encouraged via a paired inverse network rather than enforced through the numerical integration required by prior monotone calibrators; this avoids their computational overhead while empirically preserving the original classification accuracy in every setting we evaluate. Across standard image classification benchmarks and a range of architectures, InvLT consistently outperforms a broad set of post-hoc baselines on standard calibration metrics.
