Abstract Visual anomaly detection addresses the problem of classification or localization of regions in an image that deviate from their normal appearance. A popular approach trains an auto-encoder on anomaly-free images and performs anomaly detection by calculating the difference between the input and the reconstructed image. This approach assumes that the auto-encoder will be unable to accurately reconstruct anomalous regions. But in practice neural networks generalize well even to anomalies and reconstruct them sufficiently well, thus reducing the detection capabilities. Accurate reconstruction is far less likely if the anomaly pixels were not visible to the auto-encoder. We thus cast anomaly detection as a self-supervised reconstruction-by-inpainting problem. Our approach (RIAD) randomly removes partial image regions and reconstructs the image from partial inpaintings, thus addressing the drawbacks of auto-enocoding methods. RIAD is extensively evaluated on several benchmarks and sets a new state-of-the art on a recent highly challenging anomaly detection benchmark.

中文翻译：

---

通过修复重建视觉异常检测

摘要 视觉异常检测解决了图像中偏离其正常外观的区域的分类或定位问题。一种流行的方法是在无异常图像上训练自动编码器，并通过计算输入和重建图像之间的差异来执行异常检测。这种方法假设自动编码器将无法准确地重建异常区域。但在实践中，神经网络甚至可以很好地泛化到异常并充分重建它们，从而降低检测能力。如果异常像素对自动编码器不可见，则准确重建的可能性要小得多。因此，我们将异常检测作为自我监督的修复重建问题。我们的方法（RIAD）随机删除部分图像区域并从部分修复重建图像，从而解决自动编码方法的缺点。RIAD 在多个基准上进行了广泛评估，并在最近极具挑战性的异常检测基准上设定了新的最新技术水平。