探索单张图像内的内在正常原型以实现通用异常检测
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection
AI总结：
针对异常检测中测试图像与训练集正常参考难以对齐的问题，提出INP-Former方法，直接从测试图像中提取内在正常原型指导重建，在多个数据集和任务上取得SOTA性能并具备零样本能力。
摘要：
异常检测（AD）在工业检测中至关重要，然而现有方法通常依赖于将测试图像与训练集中的正常参考进行“比较”。但是，外观和位置的变化往往使这些参考与测试图像的对齐变得复杂，从而限制了检测精度。我们观察到，大多数异常表现为局部变化，这意味着即使在异常图像中，仍然保留着有价值的正常信息。我们认为这些信息是有用的，并且可能与异常更加对齐，因为异常和正常信息都源自同一张图像。因此，我们不依赖训练集的外部正常性，而是提出了 INP-Former，这是一种直接从测试图像中提取内在正常原型（INPs）的新方法。具体来说，我们引入了 INP Extractor，它线性组合正常 tokens 来表示 INPs。我们进一步提出了 INP Coherence Loss，以确保 INPs 能够忠实地表示测试图像的正常性。这些 INPs 随后指导 INP-Guided Decoder 仅重建正常 tokens，并以重建误差作为异常分数。此外，我们提出了 Soft Mining Loss，以在训练期间优先处理难以优化的样本。INP-Former 在 MVTec-AD、VisA 和 Real-IAD 上的单类、多类和少样本 AD 任务中均取得了最先进的性能，使其成为 AD 的通用且普遍适用的解决方案。值得注意的是，INP-Former 还展现出一定的零样本 AD 能力。代码可在 https://github.com/luow23/INP-Former 获取。
英文摘要：
Anomaly detection (AD) is essential for industrial inspection, yet existing methods typically rely on ``comparing'' test images to normal references from a training set. However, variations in appearance and positioning often complicate the alignment of these references with the test image, limiting detection accuracy. We observe that most anomalies manifest as local variations, meaning that even within anomalous images, valuable normal information remains. We argue that this information is useful and may be more aligned with the anomalies since both the anomalies and the normal information originate from the same image. Therefore, rather than relying on external normality from the training set, we propose INP-Former, a novel method that extracts Intrinsic Normal Prototypes (INPs) directly from the test image. Specifically, we introduce the INP Extractor, which linearly combines normal tokens to represent INPs. We further propose an INP Coherence Loss to ensure INPs can faithfully represent normality for the testing image. These INPs then guide the INP-Guided Decoder to reconstruct only normal tokens, with reconstruction errors serving as anomaly scores. Additionally, we propose a Soft Mining Loss to prioritize hard-to-optimize samples during training. INP-Former achieves state-of-the-art performance in single-class, multi-class, and few-shot AD tasks across MVTec-AD, VisA, and Real-IAD, positioning it as a versatile and universal solution for AD. Remarkably, INP-Former also demonstrates some zero-shot AD capability. Code is available at:https://github.com/luow23/INP-Former.
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。
