用反事实解释计算特征到决策边界的距离，实现高精度且可解释的异常检测。
Out-of-Distribution Detection using Counterfactual Distance
- 通过反事实解释在嵌入空间中快速计算输入到决策边界的距离。
- 在CIFAR-100上达到97.05% AUROC、13.79% FPR95，优于现有方法。
- 结果可解释，适合对模型可信度要求高的实际应用场景。
准确且可解释的分布外（OOD）检测对于安全使用机器学习系统至关重要。已有研究证明，特征到决策边界的距离可用于有效识别分布外数据。本文基于此直觉，提出一种后处理的OOD检测方法：给定输入，利用反事实解释计算其到决策边界的距离。由于大型模型计算解释成本较高，我们进一步提出在嵌入空间中直接生成反事实以提升可扩展性。关键优势在于，该方法天然支持使用反事实解释来辅助理解检测结果。实验表明，本方法在CIFAR-10上达到93.50% AUROC和25.80% FPR95；在CIFAR-100上达到97.05% AUROC和13.79% FPR95；在ImageNet-200上达到92.55% AUROC和33.55% FPR95，覆盖四个OOD数据集，性能均优于当前主流方法。
原文摘要 · Abstract (English)
Accurate and explainable out-of-distribution (OOD) detection is required to use machine learning systems safely. Previous work has shown that feature distance to decision boundaries can be used to identify OOD data effectively. In this paper, we build on this intuition and propose a post-hoc OOD detection method that, given an input, calculates the distance to decision boundaries by leveraging counterfactual explanations. Since computing explanations can be expensive for large architectures, we also propose strategies to improve scalability by computing counterfactuals directly in embedding space. Crucially, as the method employs counterfactual explanations, we can seamlessly use them to help interpret the results of our detector. We show that our method is in line with the state of the art on CIFAR-10, achieving 93.50% AUROC and 25.80% FPR95. Our method outperforms these methods on CIFAR-100 with 97.05% AUROC and 13.79% FPR95 and on ImageNet-200 with 92.55% AUROC and 33.55% FPR95 across four OOD datasets
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。