通过自监督离群值合成迈向开放世界基于对象的异常检测
Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis
AI总结：
针对开放世界无类标签的对象异常检测问题，提出通过自监督学习伪类别并合成虚拟离群特征的方法，在多模态数据集上实现SOTA性能，显著提升了召回率。
摘要：
目标检测是计算机视觉中的一项关键任务，近年来受到了广泛关注。然而，检测器对训练分布外对象进行定位的能力仍未被探索。虽然近期在对象级分布外（OoD）检测的方法严重依赖类标签，但此类方法与类别分布通常未知的真正开放世界场景相矛盾。在此背景下，异常检测侧重于检测未见实例，而非将检测结果分类为OoD。本工作旨在通过虚拟离群值合成，结合开放世界目标检测器和OoD检测器来弥合这一差距。具体而言，该方法利用检测器骨干特征，首先通过自监督学习对象的伪类别。这些伪类别作为类条件虚拟离群值采样的基础，用于采样异常特征，并由OoD头进行分类。我们的方法使整体目标检测器架构能够在不依赖类标签的情况下学习异常感知特征表示，从而实现真正的开放世界对象异常检测。对我们方法的实证验证证明了其在涵盖多种成像模态（可见光、红外和X射线）的多样数据集上的有效性。此外，我们的方法在对象级异常检测上确立了最先进的性能，与当前方法相比，在自然图像上平均召回率得分提升了5.4%以上，在安全X射线数据集上提升了23.5%。另外，我们的方法还能在当前方法失效的数据集中检测出异常。代码可在 https://github.com/KostadinovShalon/oln-ssos 获取。
英文摘要：
Object detection is a pivotal task in computer vision that has received significant attention in previous years. Nonetheless, the capability of a detector to localise objects out of the training distribution remains unexplored. Whilst recent approaches in object-level out-of-distribution (OoD) detection heavily rely on class labels, such approaches contradict truly open-world scenarios where the class distribution is often unknown. In this context, anomaly detection focuses on detecting unseen instances rather than classifying detections as OoD. This work aims to bridge this gap by leveraging an open-world object detector and an OoD detector via virtual outlier synthesis. This is achieved by using the detector backbone features to first learn object pseudo-classes via self-supervision. These pseudo-classes serve as the basis for class-conditional virtual outlier sampling of anomalous features that are classified by an OoD head. Our approach empowers our overall object detector architecture to learn anomaly-aware feature representations without relying on class labels, hence enabling truly open-world object anomaly detection. Empirical validation of our approach demonstrates its effectiveness across diverse datasets encompassing various imaging modalities (visible, infrared, and X-ray). Moreover, our method establishes state-of-the-art performance on object-level anomaly detection, achieving an average recall score improvement of over 5.4% for natural images and 23.5% for a security X-ray dataset compared to the current approaches. In addition, our method detects anomalies in datasets where current approaches fail. Code available at https://github.com/KostadinovShalon/oln-ssos.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
