基于多分辨率熵估计的VLMs零样本OOD检测层选择
Layer Selection in VLMs for Zero-Shot OOD Detection via Multi-Resolution Entropy Estimation
浏览论文内容
中文总结 AI 辅助
针对医疗图像零样本OOD检测中固定用最终层嵌入的局限，提出多分辨率熵估计策略，稳健选择中间层，在两个基准上优于现有方法。
中文摘要 AI 辅助
分布外（OOD）检测对于医疗AI系统的安全部署至关重要，因为在不同机构、采集协议和患者群体之间会出现领域偏移。视觉语言模型（VLMs）通过将图像嵌入到与语言对齐的潜在空间来实现零样本OOD检测，其中跨模态相似性作为识别分布内样本的非参数置信信号。然而，现有方法几乎完全依赖最终层的嵌入，隐含地假设最深的表示普遍最优。我们首先证明这一假设在医学影像中不成立：中间层提供互补的OOD信号，且最优表示深度取决于各自的图像模态。虽然先前的工作通过归一化直方图的熵最小化来选择层组合，但我们证明单分辨率熵估计对分箱选择高度敏感，导致AUROC性能变化高达19.3%。为解决这一不稳定性，我们提出一种多分辨率熵估计策略，该策略聚合多个离散化尺度上的直方图统计量，从而实现稳健且稳定的中间层选择。在两个医学OOD基准（即MIDOG和OASIS）上，涵盖不同的成像模态、多样的偏移类型和不同的VLM骨干网络，我们的方法持续优于最先进的方法，为零样本OOD检测提供了一种轻量级且稳定的解决方案。
英文摘要
Out-of-distribution (OOD) detection is crucial for safe deployment of medical AI systems, where domain shifts arise across institutions, acquisition protocols, and patient populations. VLMs enable zero-shot OOD detection by embedding images into a language-aligned latent space, where cross-modal similarity serves as a non-parametric confidence signal for identifying in-distribution samples. Yet existing methods rely almost exclusively on final-layer embeddings, implicitly assuming that the deepest representations are universally optimal. We first show that this assumption does not hold in medical imaging: intermediate layers provide complementary OOD signals, and the optimal representational depth depends on the respective image modality. While prior work selects layer combinations via entropy minimization of normalized histograms, we demonstrate that single-resolution entropy estimation is highly sensitive to binning choices, leading to performance variations of up to 19.3% AUROC. To address this instability, we propose a multi-resolution entropy estimation strategy that aggregates histogram statistics across multiple discretization scales, enabling robust and stable intermediate-layer selection. Across two medical OOD benchmarks, namely MIDOG and OASIS, covering distinct imaging modalities, diverse shift types, and different VLM backbones, our method consistently outperforms state-of-the-art approaches, offering a lightweight and stable solution for zero-shot OOD detection.
发表机构
- University of Bamberg（班贝格大学）
机构由 AI 辅助整理，请以论文原文为准。
