Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks

ArXi:2606.02042v1 Announce Type: new Continual industrial anomaly detection with diffusion models suffers from historical normality prior drift and catastrophic forgetting. Existing continual diffusion methods preserve previous knowledge through replay or constrained optimization, but they lack an explicit mechanism for isolating and protecting category-specific normality priors during sequential adaptation.