arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.16115cs.LGcs.CVstat.ML
收藏

基于最优传输评分函数的分布外样本检测

Detecting OOD Samples via Optimal Transport Scoring Function

ISTBI Fudan University(复旦大学ISTBI);School of Computer Science Fudan University(复旦大学计算机科学学院)

Heng Gao, Zhuolin He, Jian Pu

AI总结:

针对现有事后OOD检测方法难以捕捉网络表征几何线索的问题,提出基于最优传输理论的OTOD评分函数,融合多空间信息计算OOD分数,在多个基准上性能优于现有最优方法,并提供理论保证。

摘要:

为了在现实世界中部署机器学习模型,研究人员提出了众多分布外(OOD)检测算法,以帮助模型在推理阶段识别未知样本,避免做出不可信的预测。与依赖额外数据进行离群点暴露训练的方法不同,事后检测方法通过构建评分函数来识别OOD样本,这类方法具有模型无关性,无需额外训练。但以往的事后方法可能无法捕捉网络表征中蕴含的几何线索。因此,本研究提出了一种基于最优传输理论的新型评分函数OTOD,用于OOD检测。我们利用特征、logits(对数概率)和softmax概率空间的信息,计算每个测试样本的OOD分数。实验表明,融合这些信息能在一定程度上提升OTOD的性能。在CIFAR-10和CIFAR-100基准上的实验验证了该方法的优异性能。值得注意的是,在以ResNet-18为骨干网络的CIFAR-10基准测试中,OTOD的平均FPR@95比当前最优方法GEN低7.19%;在以WideResNet-28为骨干网络的测试中,平均FPR@95比GEN低12.51%。此外,我们还为OTOD提供了理论保证。代码可在https://github.com/HengGao12/OTOD获取。

英文摘要:

To deploy machine learning models in the real world, researchers have proposed many OOD detection algorithms to help models identify unknown samples during the inference phase and prevent them from making untrustworthy predictions. Unlike methods that rely on extra data for outlier exposure training, post hoc methods detect Out-of-Distribution (OOD) samples by developing scoring functions, which are model agnostic and do not require additional training. However, previous post hoc methods may fail to capture the geometric cues embedded in network representations. Thus, in this study, we propose a novel score function based on the optimal transport theory, named OTOD, for OOD detection. We utilize information from features, logits, and the softmax probability space to calculate the OOD score for each test sample. Our experiments show that combining this information can boost the performance of OTOD with a certain margin. Experiments on the CIFAR-10 and CIFAR-100 benchmarks demonstrate the superior performance of our method. Notably, OTOD outperforms the state-of-the-art method GEN by 7.19% in the mean FPR@95 on the CIFAR-10 benchmark using ResNet-18 as the backbone, and by 12.51% in the mean FPR@95 using WideResNet-28 as the backbone. In addition, we provide theoretical guarantees for OTOD. The code is available in https://github.com/HengGao12/OTOD.

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。

↑