发表机构
Institute of Visual Computing, Graz University of Technology; KESTRELEYE GmbH（格拉茨工业大学视觉计算研究所; KESTRELEYE有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出PRISM，一种模型无关的事后OOD检测方法，通过融合多层特征并建模统一子空间，结合马氏距离与残差能量，以单一配置在跨域基准上实现最先进性能。
AI 中文摘要
分布外（OOD）检测对于神经网络而言仍是一项基本挑战，因为网络对偏离训练分布的输入可能会给出过度自信的预测。大多数事后（post-hoc）OOD检测方法从单一表示层级（例如，logits或倒数第二层特征）推导分数，或通过深度选择或OOD校准加权来组合多个层。然而，由于OOD偏移具有多样性，最具信息量的表示层级在不同OOD类型和领域之间可能差异很大，这使得固定层选择和OOD校准聚合变得脆弱。在本文中，我们提出PRISM（带中间层子空间建模的投影表示），一种模型无关的事后OOD检测方法，该方法对统一的多层特征表示进行建模，而非对独立评分的层进行聚合。PRISM将中间层和深层特征融合为单一的分层嵌入，估计分布内（ID）主子空间，然后结合两种互补信号：（i）在投影子空间中的类条件马氏距离，以及（ii）与学习流形正交的残差能量。这种简单设计避免了针对OOD调整的层权重，同时捕获子空间内的语义偏差和子空间外的异常。在涵盖自然图像、医学影像和工业视觉检测的多个基准测试中，PRISM在所有评估领域和架构上以单一默认配置实现了持续的最先进跨域OOD检测性能。我们进一步表明，PRISM引入的推理开销极小，使其适用于实际部署。
英文摘要
Out-of-Distribution (OOD) detection remains a fundamental challenge for neural networks, whose predictions can be overconfident on inputs that deviate from the training distribution. Most post-hoc OOD detection methods derive scores from a single representation level (eg., logits or penultimate features) or combine multiple layers via depth selection or OOD-calibrated weighting. However, because OOD shifts are diverse, the most informative representation level can vary strongly across OOD types and domains, making fixed-layer choices and OOD-calibrated aggregation brittle. In this paper, we propose PRISM (Projected Representation with Intermediate-layer Subspace Modeling), a model-agnostic post-hoc OOD detection method that models a unified multi-layer feature representation rather than aggregating independently scored layers. PRISM fuses intermediate and deep features into a single hierarchical embedding, estimates an in-distribution (ID) principal subspace, and then combines two complementary signals: (i) a class-conditional Mahalanobis distance in the projected subspace and (ii) the residual energy orthogonal to the learned manifold. This simple design avoids OOD-tuned layer weighting while capturing both in-subspace semantic deviations and off-subspace anomalies. Across diverse benchmarks spanning natural images, medical imaging, and industrial visual inspection, PRISM achieves consistent state-of-the-art cross-domain OOD detection performance with a single default configuration across all evaluated domains and architectures. We further show that PRISM incurs minimal inference overhead, making it practical for real-world deployment.
CommentsECCV 2026, Code: https://github.com/gkrumpl/prism
