What Memory Composition Does Not Tell Us About Anomaly Detection

2026-08-24

AI Summary

研究探讨了基于记忆的异常检测方法在稀疏训练污染下的表现，通过对比不同选择器并使用CLEANCON减少污染，但发现最低污染不等于最高性能。

Abstract

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

Problem

• Memory-based anomaly detectors
• sparse training contamination
• memory coverage

Innovation

• CLEANCON
• Memory Contamination
• Anomaly Detection
• Coverage Selector