解决变分自编码器中重建与异常检测的矛盾问题
Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection
- 提出贝塔调度和稀疏VAE缓解重建与检测的权衡
- 稀疏VAE在保持高重建质量的同时提升检测性能
- 发现随机种子差异源于正常与异常分布距离
变分自编码器广泛用于无监督异常检测，但模型选择仍存挑战：为保持完全无监督，通常以最小化正常样本的重建误差来调整超参数。本文揭示了β-VAE模型中重建质量与异常检测性能之间的权衡：受限的隐空间虽提升检测指标，但降低重建质量。我们评估了不同随机种子下的性能波动，发现其与正常与异常隐变量分布间的距离相关。基于此分析，提出了两种缓解该权衡的方法：贝塔调度和稀疏VAE。后者尤其表现出在维持高重建质量的同时显著提升检测效果。
原文摘要 · Abstract (English)
Variational autoencoders are widely used for unsupervised anomaly detection. Model selection however remains an open-question: to remain fully unsupervised, hyperparameters are often chosen to minimize the reconstruction error on normal samples. In this paper, we reveal a trade-off between reconstruction quality and anomaly detection among $β$-VAE models. Models with constrained latent space reach higher detection metrics but lower reconstruction quality. We also assess the performance variability across random seeds and show it is linked to the distance between normal and abnormal latent distributions. From this analysis, we justify and investigate two methods to mitigate the reconstructiondetection tradeoff: beta-scheduling and the Sparse VAE. The latter especially shows an improvement in detection while maintaining high reconstruction quality.
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。