Abstract
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.
Abstract (translated)
异常分布（OOD，Out-of-Distribution）检测的任务是识别那些与训练数据分布不同的输入。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。在这项工作中，我们提出了一种事后方法——扰动矫正异常检测（PRO），基于这样的见解：对于异常分布的输入，其预测置信度更易受到扰动的影响而降低，相比之下，在分布内（IND）的输入则不然。根据这一观察结果，我们提出了一个对抗性评分函数，通过应用梯度下降来寻找原始输入附近的局部最低分数。这种方法增强了在分布内和异常分布样本之间的可分离性。重要的是，此方法能够在不进行复杂的模型架构修改的情况下提升OOD检测性能。 我们在OpenOOD基准测试~\cite{yang2022openood}上进行了广泛的实验。我们的方法进一步推动了基于softmax的OOD检测的极限，并且是小规模模型中领先的事后方法之一。在经过对抗性训练的CIFAR-10模型上，PRO能够有效地检测近似异常分布的数据输入，在FPR@95指标上的表现比当前最佳的方法减少了超过10%。 这种方法不仅增强了深度学习模型处理未见过数据的能力，还为实际应用中的安全性提供了重要的保障。
URL
https://arxiv.org/abs/2503.18784
