Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection
This work addresses the challenge of controlling reconstruction generalizability in anomaly detection, which is important for applications like industrial inspection, but it appears incremental as it builds on existing autoencoder methods.
The paper tackles the problem of unsupervised anomaly detection in images by proposing a divide-and-assemble framework that modulates reconstruction capability through feature map granularity, achieving state-of-the-art performance on the MVTec AD dataset with a 10.1% improvement in AUROC score over a vanilla autoencoder.
Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruction for abnormal samples. Since the generalizability of deep neural networks is difficult to control, existing models such as autoencoder do not work well. In this work, we interpret the reconstruction of an image as a divide-and-assemble procedure. Surprisingly, by varying the granularity of division on feature maps, we are able to modulate the reconstruction capability of the model for both normal and abnormal samples. That is, finer granularity leads to better reconstruction, while coarser granularity leads to poorer reconstruction. With proper granularity, the gap between the reconstruction error of normal and abnormal samples can be maximized. The divide-and-assemble framework is implemented by embedding a novel multi-scale block-wise memory module into an autoencoder network. Besides, we introduce adversarial learning and explore the semantic latent representation of the discriminator, which improves the detection of subtle anomaly. We achieve state-of-the-art performance on the challenging MVTec AD dataset. Remarkably, we improve the vanilla autoencoder model by 10.1% in terms of the AUROC score.