CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
This work addresses the issue of sub-optimal anomaly detection in industrial inspection or medical imaging by providing a novel refinement technique, though it is incremental as it builds on existing UAD methods.
The paper tackles the problem of inaccurate matching in unsupervised anomaly detection (UAD) by introducing cost filtering, a concept borrowed from classical matching tasks, to refine anomaly scores. The result is improved detection performance, validated on MVTec-AD and VisA benchmarks, with the method serving as a generic plug-in for both reconstruction-based and embedding-based approaches.
Unsupervised anomaly detection (UAD) seeks to localize the anomaly mask of an input image with respect to normal samples. Either by reconstructing normal counterparts (reconstruction-based) or by learning an image feature embedding space (embedding-based), existing approaches fundamentally rely on image-level or feature-level matching to derive anomaly scores. Often, such a matching process is inaccurate yet overlooked, leading to sub-optimal detection. To address this issue, we introduce the concept of cost filtering, borrowed from classical matching tasks, such as depth and flow estimation, into the UAD problem. We call this approach {\em CostFilter-AD}. Specifically, we first construct a matching cost volume between the input and normal samples, comprising two spatial dimensions and one matching dimension that encodes potential matches. To refine this, we propose a cost volume filtering network, guided by the input observation as an attention query across multiple feature layers, which effectively suppresses matching noise while preserving edge structures and capturing subtle anomalies. Designed as a generic post-processing plug-in, CostFilter-AD can be integrated with either reconstruction-based or embedding-based methods. Extensive experiments on MVTec-AD and VisA benchmarks validate the generic benefits of CostFilter-AD for both single- and multi-class UAD tasks. Code and models will be released at https://github.com/ZHE-SAPI/CostFilter-AD.