通过正交LoRA库保持正态性的持续工业异常检测
Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks
AI总结：
提出基于历史冻结正交LoRA库和分层新颖性自适应库增长模块的框架，解决扩散模型在持续工业异常检测中的历史正态先验漂移和灾难性遗忘问题。
摘要：
基于扩散模型的持续工业异常检测面临历史正态先验漂移和灾难性遗忘问题。现有的持续扩散方法通过回放或约束优化保留先前知识，但缺乏在顺序适应过程中隔离和保护类别特定正态先验的显式机制。尽管低秩适应提供了模块化残差更新，但标准LoRA既未冻结历史正态子空间，也未阻止新适配器干扰先前适配器。为解决此问题，我们提出基于两个模块的正态保持持续异常检测框架：历史冻结正交LoRA库（HF-OLB）和分层新颖性自适应库增长模块（HNABG）。HF-OLB冻结预训练的U-Net主干和已学习的LoRA库，并将新任务特定的正态残差约束到历史LoRA子空间的正交补空间中。HNABG进一步分配层依赖的残差容量，并仅在残差正态新颖性超过现有库的表达容量时扩展库。在MVTec和VisA上的大量实验证明了所提方法的有效性。在具有挑战性的VisA 2x6设置下，我们的方法实现了83.6/91.8的图像和像素级A-AUROC，以及3.8/3.9的FM，将像素级A-AUROC提升了3.2个百分点，同时将像素级FM降低了1.3。这些结果表明，我们的方法在长时间跨度的持续类别序列中有效保留了历史正态先验。
英文摘要：
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. Although low-rank adaptation provides modular residual updates, standard LoRA neither freezes historical normality subspaces nor prevents new adapters from interfering with previous ones. To address this issue, we propose a normality-preserving continual anomaly detection framework based on two modules: History Frozen Orthogonal LoRA Bank (HF-OLB) and Hierarchical Novelty Adaptive Bank Growth module (HNABG). HF-OLB freezes both the pre-trained U-Net backbone and the learned LoRA banks, and constrains new task-specific normality residuals to the orthogonal complement of historical LoRA subspaces. HNABG further allocates layer-dependent residual capacity and expands the bank only when the residual normality novelty exceeds the expressive capacity of existing banks. Extensive experiments on MVTec and VisA demonstrate the effectiveness of the proposed method. On the challenging VisA 2x6 setting, our method achieves 83.6/91.8 image and pixel level A-AUROC with 3.8/3.9 FM, improving pixel level A-AUROC over the state of the art by 3.2 points while reducing pixel level FM by 1.3. These results show that our method effectively preserves historical normality priors in long horizon continual category sequences.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
