内存异常检测中，记忆污染程度无法反映模型性能优劣。
What Memory Composition Does Not Tell Us About Anomaly Detection
- 用全局覆盖选择法会过度包含稀疏异常样本
- 新方法CLEANCON将内存污染降至接近零
- 性能随污染上升仍提升，说明污染非性能指标
基于内存的异常检测器通过存储正常训练图像块并在测试时评分来工作。然而，被选入内存的图像块作为正常参考时，未经过几何罕见性验证，可能引入异常。本文在固定表示与内存预算下，比较随机、中位数、局部和全局覆盖选择策略。进一步引入CLEANCON——一种基于袋外跨图像支持门的机制，在不改变表示、内存大小、构建器和推理规则的前提下，动态调整候选图像资格。结果显示，全局覆盖显著高估稀疏异常，而CLEANCON将最终内存污染降至约零，并在12组对比中均提升类别宏平均精度（P-AP）。然而，在保留率扫描中，污染最低的记忆并未达到最高P-AP，性能在污染上升时仍持续改善。因此，内存污染程度无法有效排序记忆质量与模型性能。
原文摘要 · Abstract (English)
Memory-based anomaly detectors store nominal training patches and score test patches against this memory. A patch selected for coverage therefore becomes a nor- mal reference without a separate check that geometric rarity makes it safe to trust. We probe this coupling with sparse training contamination. Under fixed representa- tions and memory budgets, we compare random, medoid, local, and global coverage selectors. We then use CLEANCON, an out-of-bag cross-image support gate that changes candidate-image eligibility while fixing the representation, absolute mem- ory size, builder, and inference rule. Global coverage strongly over-represents sparse contamination. CLEANCON reduces final-memory contamination to approx- imately zero and increases category-macro P-AP in all 12 matched comparisons. Yet along a retention sweep, the lowest-contamination memory does not attain the highest P-AP; performance continues to improve while contamination rises. Mem- ory contamination therefore does not order the resulting memories by P-AP
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。