arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.09522cs.LGcs.CV
收藏

类别自适应一致性训练

Class Adaptive Conformal Training

CentraleSupélec, Université Paris-Saclay(中南大学巴黎萨克雷大学);ÉTS Montréal(蒙特利尔工程学院)

Badr-Eddine Marani, Julio Silva-Rodriguez, Ismail Ben Ayed, Maria Vakalopoulou, Stergios Christodoulidis, Jose Dolz

AI总结:

本文提出类别自适应一致性训练方法,通过自适应学习在不假设分布的情况下,改进预测集的形状和信息量,提升模型的不确定性量化能力。

摘要:

深度神经网络在各种任务中取得了显著成功,但它们常常面临不可靠的概率估计问题。因此,它们在预测上可能会过于自信。一致性预测(CP)提供了一个原则性的框架用于不确定性量化,产生具有严格覆盖保证的预测集。现有的一致性训练方法优化总体集大小,但以类别条件方式塑造预测集并不直接,通常需要数据分布的先验知识。在本工作中,我们引入了类别自适应一致性训练(CaCT),将一致性训练作为增强拉格朗日优化问题,能够自适应地学习以类别条件方式塑造预测集,而无需做出任何分布假设。在多个基准数据集上的实验,包括标准和长尾图像识别以及文本分类,表明CaCT在多个基准数据集上 consistently 超过先前的一致性训练方法,产生显著更小且更有信息量的预测集,同时保持所需的覆盖保证。

英文摘要:

Deep neural networks have achieved remarkable success across a variety of tasks, yet they often suffer from unreliable probability estimates. As a result, they can be overconfident in their predictions. Conformal Prediction (CP) offers a principled framework for uncertainty quantification, yielding prediction sets with rigorous coverage guarantees. Existing conformal training methods optimize for overall set size, but shaping the prediction sets in a class-conditional manner is not straightforward and typically requires prior knowledge of the data distribution. In this work, we introduce Class Adaptive Conformal Training (CaCT), which formulates conformal training as an augmented Lagrangian optimization problem that adaptively learns to shape prediction sets class-conditionally without making any distributional assumptions. Experiments on multiple benchmark datasets, including standard and long-tailed image recognition as well as text classification, demonstrate that CaCT consistently outperforms prior conformal training methods, producing significantly smaller and more informative prediction sets while maintaining the desired coverage guarantees.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑