INP-Former++：通过内在正常原型与残差学习推进通用异常检测
INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learning
AI总结：
本文提出INP-Former及改进版INP-Former++，通过直接从测试图像中提取内在正常原型（INPs）并利用残差学习指导正常token重建，在多类、少样本及零样本等异常检测任务上实现了最先进的通用检测性能。
摘要：
异常检测（AD）对工业检测和医疗诊断至关重要，但现有方法通常依赖将测试图像与训练集中的正常参考进行“比较”。然而，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，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，仍然存在有价值的正常信息。我们认为这些信息是有用的，并且可能更与异常对齐，因为异常和正常信息都源自同一图像。因此，我们不依赖训练集的外部正常性，而是提出了INP-Former，一种直接从测试图像中提取内在正常原型（INPs）的新方法。具体而言，我们引入了INP Extractor，它线性组合正常token来表示INPs。我们进一步提出INP Coherence Loss以确保INPs能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token，重建误差作为异常分数。此外，我们提出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任务中取得了最先进的性能，使其成为AD的通用和普适解决方案。值得注意的是，INP-Former还展现出一定的零样本AD能力。此外，我们提出了INP Coherence Loss的软版本，并通过结合残差学习增强了INP-Former，从而开发了INP-Former++。所提出的方法显著提升了单类、多类、半监督、少样本和零样本设置下的检测性能。
英文摘要：
Anomaly detection (AD) is essential for industrial inspection and medical diagnosis, 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. Furthermore, we propose a soft version of the INP Coherence Loss and enhance INP-Former by incorporating residual learning, leading to the development of INP-Former++. The proposed method significantly improves detection performance across single-class, multi-class, semi-supervised, few-shot, and zero-shot settings.
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。
