面向三维工业异常检测的自监督特征适配
Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection
AI总结：
本文针对三维工业异常检测中预训练模型领域差异问题，提出局部到全局的自监督特征适配方法LSFA，通过模态内适配与跨模态对齐提升特征表示质量，在MVTec-3D AD和Eyecandies数据集上显著超越现有方法。
摘要：
工业异常检测通常被处理为一种无监督任务，其目标是在仅有正常训练样本的情况下定位缺陷。近年来，大量二维异常检测方法被提出并取得了有前景的结果，然而仅使用二维RGB数据作为输入不足以识别难以察觉的几何表面异常。因此，本文聚焦于多模态异常检测。具体而言，我们研究了早期的多模态方法，这些方法尝试利用在大规模视觉数据集（即ImageNet）上预训练的模型来构建特征数据库。我们通过实验发现，直接使用这些预训练模型并非最优，它可能无法检测细微缺陷，或者将异常特征误判为正常特征。这可能是由于目标工业数据与源数据之间存在领域差异。针对这一问题，我们提出了一种局部到全局的自监督特征适配（LSFA）方法，用于微调适配器并学习面向异常检测的任务导向表示。在LSFA中，模态内适配和跨模态对齐均从局部到全局的角度进行优化，以确保推理阶段的表示质量和一致性。大量实验表明，我们的方法不仅为基于特征嵌入的方法带来了显著的性能提升，而且在MVTec-3D AD和Eyecandies数据集上均显著优于先前的最先进（SoTA）方法，例如，LSFA在MVTec-3D上实现了97.1%的I-AUROC，比先前SoTA高出+3.4%。
英文摘要：
Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples. Recently, numerous 2D anomaly detection methods have been proposed and have achieved promising results, however, using only the 2D RGB data as input is not sufficient to identify imperceptible geometric surface anomalies. Hence, in this work, we focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets, i.e., ImageNet, to construct feature databases. And we empirically find that directly using these pre-trained models is not optimal, it can either fail to detect subtle defects or mistake abnormal features as normal ones. This may be attributed to the domain gap between target industrial data and source data.Towards this problem, we propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.Both intra-modal adaptation and cross-modal alignment are optimized from a local-to-global perspective in LSFA to ensure the representation quality and consistency in the inference stage.Extensive experiments demonstrate that our method not only brings a significant performance boost to feature embedding based approaches, but also outperforms previous State-of-The-Art (SoTA) methods prominently on both MVTec-3D AD and Eyecandies datasets, e.g., LSFA achieves 97.1% I-AUROC on MVTec-3D, surpass previous SoTA by +3.4%.
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。
