CASCADE: Constraint-Aware Scaffolded Decomposition for Logical Anomaly Detection
The paper identifies a text-image mismatch in LVLM-based logical anomaly detection, where checklist items all read the same raw image, leading to instance conflation and scale drift. It finds that adapting the visual input per constraint helps substantially more than textual reasoning guides in a training-free setting. CASCADE extends checklist decomposition with constraint-specific visual scaffolds, and CASCADE++ derives object-level scaffold configurations from constraint structure and reference distribution. Across MVTec-LOCO and VID-AD, CASCADE++ is reported to surpass the full-shot state of the art by 3.9 AUROC points using only three references and to improve over the strongest VID-AD baseline by 11.4, transferring across LVLM backbones without training.
It offers a concrete, training-free technique that improves few-shot logical anomaly detection and explains why visual, rather than textual, constraint adaptation matters.
Comments & Questions (0)
No comments yet
Be the first to comment!