arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.18784cs.CV
收藏

利用扰动鲁棒性增强分布外检测

Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection

Purdue University(普渡大学)

Wenxi Chen, Raymond A. Yeh, Shaoshuai Mou, Yan Gu

AI总结:

本研究提出后处理方法PRO,利用分布外输入预测置信度对扰动更敏感的特性,通过梯度下降搜索局部最低评分提升分布内外样本可分性,在OpenOOD基准上刷新小模型softmax类OOD检测性能,CIFAR-10对抗训练模型上FPR@95降超10%。

摘要:

分布外(OOD)检测是识别偏离训练数据分布的输入的任务,这一能力对于在开放世界环境中安全部署深度计算机视觉模型至关重要。本研究提出了一种后处理方法——扰动校正分布外检测(PRO),其核心洞察是:分布内(IND)输入的预测置信度在扰动下的下降幅度小于分布外输入。基于这一观察,我们提出了一种对抗性评分函数,通过梯度下降搜索原始输入附近的局部最低评分,该过程提升了分布内与分布外样本的可分性。重要的是,该方法无需对底层模型架构进行复杂修改即可提升分布外检测性能。我们使用OpenOOD基准开展了大量实验,该方法进一步突破了基于softmax的分布外检测的性能上限,是小尺度模型中性能领先的后处理方法。在经过对抗训练的CIFAR-10模型上,PRO可有效检测近分布外输入,与当前最优方法相比,FPR@95降低超过10%。

英文摘要:

Out-of-distribution (OOD) detection is the task of identifying inputs that deviate from the training data distribution. This capability is essential for safely deploying deep computer vision models in open-world environments. In this work, we propose a post-hoc method, Perturbation-Rectified OOD detection (PRO), based on the insight that prediction confidence for OOD inputs is more susceptible to reduction under perturbation than in-distribution (IND) inputs. Based on the observation, we propose an adversarial score function that searches for the local minimum scores near the original inputs by applying gradient descent. This procedure enhances the separability between IND and OOD samples. Importantly, the approach improves OOD detection performance without complex modifications to the underlying model architectures. We conduct extensive experiments using the OpenOOD benchmark~\cite{yang2022openood}. Our approach further pushes the limit of softmax-based OOD detection and is the leading post-hoc method for small-scale models. On a CIFAR-10 model with adversarial training, PRO effectively detects near-OOD inputs, achieving a reduction of more than 10\% on FPR@95 compared to state-of-the-art methods.

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。

↑