打破偏差：重新校准工业异常检测的注意力
Breaking the Bias: Recalibrating the Attention of Industrial Anomaly Detection
AI总结：
针对无监督工业异常检测中正常样本固有偏差导致的注意力错配问题，提出RAAD框架，通过分层量化评分动态调整各层位宽以校准注意力，在32个数据集上验证了其在平衡效率与检测能力上的有效性。
摘要：
由于缺陷样本具有稀缺性和不可预测性，工业异常检测（IAD）主要采用无监督学习方法。然而，所有无监督IAD方法都面临一个共同挑战：正常样本中存在的固有偏差会导致模型聚焦于可变区域，却忽略了不变区域内的潜在缺陷。为有效克服这一问题，必须对注意力进行分解与重新校准，引导模型抑制无关变化，专注于细微的、易出现缺陷的区域。本文提出了RAAD（重新校准工业异常检测注意力）框架，该框架可系统地分解并重新校准注意力图。RAAD采用两阶段流程：首先通过量化降低注意力偏差，其次对易出现缺陷的区域进行微调以提升敏感度。该框架的核心是分层量化评分（HQS），它根据各层的异常检测贡献动态分配位宽。HQS依据注意力图的分层特性动态调整位宽，压缩生成粗糙、含噪注意力的低层，同时保留具有更清晰、聚焦于缺陷的注意力的深层。该方法同时优化了计算效率和模型对异常的敏感度。我们在32个数据集上使用单张3090ti验证了RAAD的有效性。实验表明，RAAD平衡了模型的复杂度和表达能力，提升了其异常检测性能。
英文摘要：
Due to the scarcity and unpredictable nature of defect samples, industrial anomaly detection (IAD) predominantly employs unsupervised learning. However, all unsupervised IAD methods face a common challenge: the inherent bias in normal samples, which causes models to focus on variable regions while overlooking potential defects in invariant areas. To effectively overcome this, it is essential to decompose and recalibrate attention, guiding the model to suppress irrelevant variations and concentrate on subtle, defect-susceptible areas. In this paper, we propose Recalibrating Attention of Industrial Anomaly Detection (RAAD), a framework that systematically decomposes and recalibrates attention maps. RAAD employs a two-stage process: first, it reduces attention bias through quantization, and second, it fine-tunes defect-prone regions for improved sensitivity. Central to this framework is Hierarchical Quantization Scoring (HQS), which dynamically allocates bit-widths across layers based on their anomaly detection contributions. HQS dynamically adjusts bit-widths based on the hierarchical nature of attention maps, compressing lower layers that produce coarse and noisy attention while preserving deeper layers with sharper, defect-focused attention. This approach optimizes both computational efficiency and the model' s sensitivity to anomalies. We validate the effectiveness of RAAD on 32 datasets using a single 3090ti. Experiments demonstrate that RAAD, balances the complexity and expressive power of the model, enhancing its anomaly detection capability.
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。
