从不精确标注中的认知学习

中文摘要 AI 辅助

不精确的标注可能支持多种合理的标签分布，然而学习方法常常将这种模糊性解析为单一的预测分布。这可能掩盖标注证据未解决的内容。我们引入了从信度监督中进行认知学习，这是一个使用凸集形式的合理标签分布（称为信度集）作为监督，并学习预测分布集的框架。我们用悲观-乐观信度分类器（POCC）实例化该框架，它结合了一个共享骨干网络与两个分类头，分别训练以最小化监督集上的最坏情况和最好情况损失。它们的输出定义了一个预测信度集，其离散程度提供了不确定性分数。我们还展示了如何通过简单松弛现有概率标签来获得信度标签，减少对其精确概率分配的承诺。这种构造在交叉熵损失下允许闭式内优化，从而实现高效训练。假设监督集包含真实的条件标签分布，以及其他正则性假设，我们为平均预测器建立了一个有限样本泛化界，并带有对监督不精确性的显式惩罚。我们使用人类标注者分歧和教师预测来评估POCC，同时将标签平滑作为标注不精确性的受控代理。在这些设置中，与竞争性基线相比，POCC在预测准确性、校准和基于不确定性的选择性分类之间取得了有利的平衡。

英文摘要

Imprecise annotations may support several plausible labelling distributions, yet learning methods often resolve this ambiguity into a single predictive distribution. This can obscure what the annotation evidence leaves unresolved. We introduce epistemic learning from credal supervision, a framework that uses convex sets of plausible labelling distributions, called credal sets, as supervision and learns sets of predictive distributions. We instantiate the framework with the pessimistic--optimistic credal classifier (POCC), which combines a shared backbone with two classification heads trained to minimise worst-case and best-case losses over the supervision sets. Their outputs define a predictive credal set whose spread provides an uncertainty score. We also show how credal labels can be obtained through a simple relaxation of existing probabilistic labels, reducing commitment to their precise probability assignments. This construction admits closed-form inner optimisation under cross-entropy loss, enabling efficient training. Assuming the supervision sets contain the true conditional label distributions, and other regularity assumptions, we establish a finite-sample generalisation bound for the averaged predictor with an explicit penalty for supervision imprecision. We evaluate POCC using human annotator disagreement and teacher predictions, alongside label smoothing as a controlled proxy for annotation imprecision. Across these settings, POCC achieves a favourable balance of predictive accuracy, calibration, and uncertainty-based selective classification versus competitive baselines.

发表机构

• Nanyang Technological University（南洋理工大学）

机构由 AI 辅助整理，请以论文原文为准。