学习潜在概念用于分布外目标检测
Learning Latent Concepts for Detecting Out-of-Distribution Objects
提出基于槽位表征的无监督概念发现与神经概念绑定器，将未知概念注入检测器，为开放世界目标检测中的OOD识别提供可复用的框架。
原文依据 we propose UNO-Adapter, a simple yet highly effective framework tailored for OOD object detection
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论检测分布外（OOD）目标对于在真实环境中安全部署目标检测器不可或缺。当前方法通过正则化实例级特征空间（如异常值合成）来赋予模型未知感知能力。尽管普遍有效，但在缺乏真实未知数据的情况下，真正学习“未知”的概念仍具挑战性。本文提出UNO-Adapter，一个简单却高效的OOD目标检测框架。我们的关键洞察是：在目标检测中，分布内（ID）与OOD目标可能共存于同一上下文，需要全局抽象与推理来帮助检测器学习它们的差异，即未知注入。UNO-Adapter包含两个关键步骤：无监督概念发现与神经概念绑定器。前者引入以对象为中心的学习范式，对包含ID和OOD的整体图像进行抽象与建模，获得具有关系约束的稀疏压缩槽位表征。后者将槽位与检测器提取的候选对象动态结合，将未知概念绑定到实际检测器。推理时，我们引入图像引导的OOD目标评分以强化ID与OOD的区分。标准基准上的实验证明了所提方法的优越性。特别地，与之前最佳的OOD目标检测方法相比，UNO-Adapter将FPR95最多降低11.96%。
英文原文摘要 1496 字符
Detecting out-of-distribution (OOD) objects is indispensable for safely deploying object detectors in the wild. Current approaches enable the unknown-aware ability by regularizing the instance-level feature space, such as outlier synthesis. Despite the general efficacy, it is challenging to truly learn the concept of 'unknown' under the absence of real unknown data. In this paper, we propose UNO-Adapter, a simple yet highly effective framework tailored for OOD object detection. Our key insight is that in object detection, where in-distribution (ID) and OOD objects may coexist within the same context, we need global abstraction and reasoning to help the detector learn their differences, i.e., unknown injection. UNO-Adapter consists of two key steps: unsupervised concept discovery and neural concept binder. The former introduces an object-centric learning paradigm to abstract and model the holistic image, including both ID and OOD, obtaining sparse and compressed slot-based representations with relational constraints. The latter dynamically combines slots with object candidates extracted by the detector, binding the concept of unknown to the de facto detector. During inference, we introduce an image-guided OOD object score to reinforce the distinction between ID and OOD. Experiments on standard benchmarks demonstrate the superiority of the proposed method. In particular, UNO-Adapter reduces the FPR95 by up to 11.96% compared to the previous best OOD object detection method.