arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.01596cs.CV
收藏

FEVER-OOD:面向鲁棒分布外检测的自由能脆弱性消除

FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection

Durham University(杜伦大学);University of Vienna(维也纳大学);Intel Corporation(英特尔公司)

Brian K. S. Isaac-Medina, Mauricio Che, Yona F. A. Gaus, Samet Akcay, Toby P. Breckon

AI总结:

针对自由能分数因分类器末层零空间而无法区分分布内与OOD样本的问题,本文提出FEVER-OOD,通过低维特征空间和最小奇异值正则化增强自由能分离,并在Imagenet-100上取得最优检测性能。

摘要:

在分类和目标检测等计算机视觉任务上表现出色的现代机器学习模型,往往对其针对分布外(OOD)样本的预测过度自信,从而在开集环境中导致不可预测的行为。近期研究表明,自由能分数与数据分布关系密切,因此是用于OOD检测的一种有效不确定性度量。然而,尽管基于自由能的方法在OOD检测中代表了重要的经验进展,我们的理论分析揭示了自由能分数公式中此前未被探索且固有的脆弱性:分布内样本与OOD实例可能具有不同的特征表示,却拥有完全相同的自由能分数。当表示分布内样本与OOD样本之间特征空间差异的向量方向位于基于神经网络的分类器最后一层的零空间内时,就会出现这种现象。为缓解这些问题,我们探索低维特征空间以减小零空间覆盖范围,并引入新的正则化来最大化最终线性层的最小奇异值,从而增强样本间的自由能分离度。我们将这些技术称为面向鲁棒分布外检测的自由能脆弱性消除(Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection,FEVER-OOD)。实验表明,FEVER-OOD技术在Imagenet-100上实现了最先进的OOD检测;当与基线Dream-OOD模型结合使用时,在95%真阳性率下的平均OOD假阳性率为35.83%。

英文摘要:

Modern machine learning models, that excel on computer vision tasks such as classification and object detection, are often overconfident in their predictions for Out-of-Distribution (OOD) examples, resulting in unpredictable behaviour for open-set environments. Recent works have demonstrated that the free energy score is an effective measure of uncertainty for OOD detection given its close relationship to the data distribution. However, despite free energy-based methods representing a significant empirical advance in OOD detection, our theoretical analysis reveals previously unexplored and inherent vulnerabilities within the free energy score formulation such that in-distribution and OOD instances can have distinct feature representations yet identical free energy scores. This phenomenon occurs when the vector direction representing the feature space difference between the in-distribution and OOD sample lies within the null space of the last layer of a neural-based classifier. To mitigate these issues, we explore lower-dimensional feature spaces to reduce the null space footprint and introduce novel regularisation to maximize the least singular value of the final linear layer, hence enhancing inter-sample free energy separation. We refer to these techniques as Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection (FEVER-OOD). Our experiments show that FEVER-OOD techniques achieve state of the art OOD detection in Imagenet-100, with average OOD false positive rate (at 95% true positive rate) of 35.83% when used with the baseline Dream-OOD model.

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。

↑