In this paper, we propose a framework called TrustMAE to address the problem of product defect classification. Instead of relying on defective images that are difficult to collect and laborious to label, our framework can accept datasets with unlabeled images. Moreover, unlike most anomaly detection methods, our approach is robust against noises, or defective images, in the training dataset. Our framework uses a memory-augmented auto-encoder with a sparse memory addressing scheme to avoid over-generalizing the auto-encoder, and a novel trust-region memory updating scheme to keep the noises away from the memory slots. The result is a framework that can reconstruct defect-free images and identify the defective regions using a perceptual distance network. When compared against various state-of-the-art baselines, our approach performs competitively under noise-free MVTec datasets. More importantly, it remains effective at a noise level up to 40% while significantly outperforming other baselines.

本文介绍了一种名为TrustMAE的框架，该框架能够识别产品缺陷，即便没有已标注的有缺陷图像。这种方法不易受到噪声的影响，可以通过一种稀疏内存寻址方案来避免自动编码器过于泛化，并且可以通过一种新颖的信任区域内存更新方案在记忆槽中保留有用的信息和避免噪声。TrustMAE能够通过感知距离网络重建无缺陷的图像并且找到有缺陷的区域，相较于其他基线方法，在MVTec数据集上的效果有竞争力，并且在噪声等级高达40%的情况下仍然有效，远远优于其他基线方法。

TrustMAE：一种使用带有信任区域的记忆增强自编码器的噪声鲁棒性缺陷分类框架