We propose using Masked Auto-Encoder (MAE), a transformer model self-supervisedly trained on image inpainting, for anomaly detection (AD). Assuming anomalous regions are harder to reconstruct compared with normal regions. MAEDAY is the first image-reconstruction-based anomaly detection method that utilizes a pre-trained model, enabling its use for Few-Shot Anomaly Detection (FSAD). We also show the same method works surprisingly well for the novel tasks of Zero-Shot AD (ZSAD) and Zero-Shot Foreign Object Detection (ZSFOD), where no normal samples are available. Code is available at https://github.com/EliSchwartz/MAEDAY .

翻译：我们提出使用掩码自编码器（MAE，一种通过图像修复任务自监督训练的Transformer模型）进行异常检测（AD）。其核心假设是：异常区域相比正常区域更难被重建。MAEDAY是首个基于图像重建的异常检测方法，通过利用预训练模型实现少样本异常检测（FSAD）。实验表明，该方法在零样本异常检测（ZSAD）和零样本异物检测（ZSFOD）这两类新型任务中同样表现出色，且无需任何正常样本。代码开源地址：https://github.com/EliSchwartz/MAEDAY。