That's BAD: Blind Anomaly Detection by Implicit Local Feature Clustering
This addresses a more challenging scenario for industrial visual inspection, enabling anomaly detection without human annotation, though it builds incrementally on existing outlier detection approaches.
The paper tackles the problem of blind anomaly detection (BAD) in images without requiring any normal training data, converting it into a local outlier detection task, and achieves performance comparable to state-of-the-art methods that rely on normal data.
Recent studies on visual anomaly detection (AD) of industrial objects/textures have achieved quite good performance. They consider an unsupervised setting, specifically the one-class setting, in which we assume the availability of a set of normal (\textit{i.e.}, anomaly-free) images for training. In this paper, we consider a more challenging scenario of unsupervised AD, in which we detect anomalies in a given set of images that might contain both normal and anomalous samples. The setting does not assume the availability of known normal data and thus is completely free from human annotation, which differs from the standard AD considered in recent studies. For clarity, we call the setting blind anomaly detection (BAD). We show that BAD can be converted into a local outlier detection problem and propose a novel method named PatchCluster that can accurately detect image- and pixel-level anomalies. Experimental results show that PatchCluster shows a promising performance without the knowledge of normal data, even comparable to the SOTA methods applied in the one-class setting needing it.