基于斯坦因算子的检测方法，能感知数据分布变化对模型任务的影响。
TASTE: Task-Aware Out-of-Distribution Detection via Stein Operators
- 利用斯坦因算子将分布偏移与模型输入敏感性关联
- 在多个数据集上检测精度优于现有基线方法
- 可定位异常区域并提供像素级解释，适合需要可解释性的场景
现有分布外检测方法要么关注训练数据分布的偏离，要么依赖分类器输出而忽略数据几何结构。本文提出TASTE（任务感知斯坦因算子）：一种基于斯坦因算子的任务感知框架，将分布偏移与模型输入敏感性联系起来。理论证明该算子可解释为分布偏移在模型敏感场上的投影，具有明确几何意义。除检测分布偏移外，该方法还可通过坐标分解实现局部定位，并对图像数据提供像素级可解释诊断。在控制高斯偏移、几何扰动下的MNIST以及受扰动的CIFAR-10基准测试中，所提方法在检测分布偏移时与任务性能下降高度一致，且优于已有基线。
原文摘要 · Abstract (English)
Out-of-distribution detection methods are often either data-centric, detecting deviations from the training input distribution irrespective of their effect on a trained model, or model-centric, relying on classifier outputs without explicit reference to data geometry. We propose TASTE (Task-Aware STEin operators): a task-aware framework based on so-called Stein operators, which allows us to link distribution shift to the input sensitivity of the model. We show that the resulting operator admits a clear geometric interpretation as a projection of distribution shift onto the sensitivity field of the model, yielding theoretical guarantees. Beyond detecting the presence of a shift, the same construction enables its localisation through a coordinate-wise decomposition, and for image data-provides interpretable per-pixel diagnostics. Experiments on controlled Gaussian shifts, MNIST under geometric perturbations, and CIFAR-10 perturbed benchmarks demonstrate that the proposed method aligns closely with task degradation while outperforming established baselines.
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。