SPK：为实时目标检测中的可分布外检测引出结构化先验知识
SPK: Eliciting Structured Prior Knowledge for Interpretable Out-of-Distribution Detection in Real-Time Object Detection
浏览论文内容
中文总结 AI 辅助
本研究提出SPK框架，从预训练目标检测器中引出结构化先验知识，构建五维表示实现最先进的分布外检测，揭示预训练检测器蕴含丰富潜在知识，为提升目标检测器可靠性提供新路径。
中文摘要 AI 辅助
目标检测器常常对训练类别之外的物体产生过度自信的预测，导致所谓的分布外（Out-of-Distribution, OoD）幻觉。现有的检测或缓解此类幻觉的方法通常要么直接在学习到的目标检测器表示上构建评分函数，要么修改目标检测器本身以抑制幻觉的出现。然而，这些表示中隐含编码的潜在先验在很大程度上仍未被探索，且尚未被明确解码用于OoD检测。为了揭示并利用这些潜在先验，我们提出了结构化先验知识（Structured Prior Knowledge, SPK），这是一个面向幻觉的框架，可从预训练的目标检测器中明确引出与OoD相关的先验。具体而言，SPK利用分布内数据和诱导幻觉的样本作为诊断监督，引出目标检测器决策背后的部件级语义概念，而非仅将它们用于拒绝或目标检测器适配。引出的语义先验进一步与几何和上下文先验相结合，形成用于OoD检测的紧凑五维SPK表示。在不同目标检测器架构和多个OoD基准上的大量实验表明，SPK实现了最先进的OoD检测性能。我们的发现表明，预训练的目标检测器已编码了比OoD检测通常利用的丰富得多的潜在知识，更重要的是，这些知识可以被明确引出并组织成紧凑、结构化且可解释的知识空间，用于预测可靠性分析，这为通过明确揭示和利用潜在先验来提高目标检测器可靠性提供了一条有前景的主动路径。代码和数据可在以下网址获取：this https URL
英文摘要
Object detectors often produce over-confident predictions for objects outside their training categories, leading to so-called out-of-distribution (OoD) hallucinations. Existing approaches for detecting or mitigating such hallucinations typically either construct scoring functions directly over learned object detector representations or modify the object detector itself to suppress hallucination emergence. However, the latent priors implicitly encoded in these representations remain largely unexplored and have not been explicitly decoded for OoD detection. To uncover and exploit these latent priors, we propose Structured Prior Knowledge (SPK), a hallucination-oriented framework that explicitly elicits OoD-relevant priors from pretrained object detectors. Specifically, SPK leverages in-distribution data and hallucination-inducing samples as diagnostic supervision to elicit part-level semantic concepts underlying object detector decision-making, rather than using them merely for rejection or object detector adaptation. The elicited semantic priors are further integrated with geometric and contextual priors to form a compact five-dimensional SPK representation for OoD detection. Extensive experiments across diverse object detector architectures and multiple OoD benchmarks demonstrate that SPK achieves state-of-the-art OoD detection. Our findings reveal that pretrained object detectors already encode substantially richer latent knowledge than is typically exploited for OoD detection. More importantly, this knowledge can be explicitly elicited and organized into a compact, structured, and interpretable knowledge space for prediction reliability analysis. This suggests a promising proactive route for improving object detector reliability by explicitly uncovering and leveraging latent priors. Code and data are available at: https://gricad-gitlab.univ-grenoble-alpes.fr/dnn-safety/spk
