无需训练，通过投影一致性检测异常，定位更准。
ProCon: Projection-Consistency Memory for Training-Free Anomaly Detection
- 将测试图像块软投影到正常记忆向量，用投影残差判断异常
- 在MVTec-AD等数据集上图像AUROC最高达99.8%，像素级性能强
- 适合无标注异常检测场景，无需调参或额外训练
基于记忆的异常检测因其无需训练解码器或生成伪异常即可定位缺陷而受到关注。然而，多数方法将记忆库视为硬性最近邻查找表：只要测试块与一个正常锚点邻近，就被判定为正常。这种机制易产生误判，且不检验该块是否被局部正常邻域持续支持。本文提出ProCon，一种无需训练的框架，将记忆检索转为无解码器重建。ProCon将每个测试块软投影到附近的正常记忆向量，以投影残差作为异常证据。为稳定残差，构建种子扰动的逐层记忆，通过中值聚合银行残差，并利用层级共识融合深度特定残差图。ProCon无需解码器训练、主干微调、可学习融合权重或伪异常监督。在MVTec-AD、VisA和Real-IAD的单类别评估协议下，其在七项标准指标上表现优异，图像AUROC分别为99.8%、99.2%和93.2%。消融实验表明，性能提升源于用软正常投影替代硬检索，并通过记忆与深度共识稳定残差。
原文摘要 · Abstract (English)
Memory-based anomaly detection is attractive because it localizes defects from normal images without training a decoder or synthesizing pseudo anomalies. However, most memory methods still use the memory bank as a nearest-neighbor lookup table: a test patch is treated as normal if it has one nearby normal anchor. This hard retrieval view is vulnerable to false-normal matches and does not test whether the patch is consistently supported by a local normal neighborhood. We propose ProCon, a training-free framework that turns memory retrieval into decoder-free reconstruction. ProCon softly projects each test patch onto nearby normal memory vectors and uses the projection residual as anomaly evidence. To stabilize this residual, it constructs seed-perturbed layer-wise memories, aggregates bank residuals by a median, and fuses depth-specific residual maps by layer consensus. ProCon requires no decoder training, backbone fine-tuning, learned fusion weights, or pseudo-anomaly supervision. Across MVTec-AD, VisA, and Real-IAD under the single-category evaluation protocol, ProCon achieves strong image- and pixel-level performance under seven standard metrics, including image AUROC scores of 99.8%, 99.2%, and 93.2%, respectively. Ablations show that the gains come from replacing hard retrieval with soft normal projection and stabilizing the residuals through memory and depth consensus. The code is available at https://github.com/jw-chae/Procon
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。