通过扰动鲁棒性提升模型对分布外数据的识别能力
Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection
- 利用输入受扰后置信度变化差异设计对抗评分函数
- 在CIFAR-10模型上使FPR@95降低超10%
- 无需修改模型结构，适合小模型部署
分布外（OOD）检测旨在识别偏离训练数据分布的输入，对开放世界中深度视觉模型的安全部署至关重要。本文提出一种后处理方法——扰动修正OOD检测（PRO），其核心思想是：分布外样本的预测置信度受扰动影响更大。为此，我们设计了一种对抗性评分函数，通过梯度下降搜索原输入附近的局部最小得分，增强分布内（IND）与分布外（OOD）样本的可分性。该方法无需复杂修改模型架构即可显著提升性能。在OpenOOD基准上进行了广泛实验，进一步推动了基于Softmax的OOD检测极限，是小规模模型上的领先后处理方法。在经过对抗训练的CIFAR-10模型上，对近似分布外输入的检测效果显著，相比最先进方法，FPR@95降低超过10%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。