用原型变分自编码器实现可解释的异常检测，提升模型可信度。
Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection
- 基于变分自编码器学习有意义的潜在空间，通过距离与似然判断异常样本。
- 引入新型约束损失，使正常数据区域紧凑但不坍缩为单点。
- 重建能力让原型和分类区域可解释，适合高安全场景应用。
理解深度学习模型的决策过程并信任其可靠性，对安全相关应用至关重要。本文扩展了自解释原型变分模型，结合自编码器实现分布外（OOD）检测：利用变分自编码器学习有意义的潜在空间，用于基于距离的分类、似然估计以识别异常样本以及重构。正常数据（ID）区域由学习得到的原型定义，这些原型代表每个模式的中心，并拟合为高斯混合分布。此外，提出一种新型约束损失，促进潜在空间中正常区域的紧凑性，同时避免其坍缩为单一点。自编码器的重构能力确保了原型和分类区域的可解释性，进一步增强了对异常样本的区分能力。在常见分布外检测基准及一个来自真实铁路应用的大规模数据集上进行了广泛评估，结果表明该方法优于以往方法。
原文摘要 · Abstract (English)
Understanding the decision-making and trusting the reliability of Deep Machine Learning Models is crucial for adopting such methods to safety-relevant applications. We extend self-explainable Prototypical Variational models with autoencoder-based out-of-distribution (OOD) detection: A Variational Autoencoder is applied to learn a meaningful latent space which can be used for distance-based classification, likelihood estimation for OOD detection, and reconstruction. The In-Distribution (ID) region is defined by a Gaussian mixture distribution with learned prototypes representing the center of each mode. Furthermore, a novel restriction loss is introduced that promotes a compact ID region in the latent space without collapsing it into single points. The reconstructive capabilities of the Autoencoder ensure the explainability of the prototypes and the ID region of the classifier, further aiding the discrimination of OOD samples. Extensive evaluations on common OOD detection benchmarks as well as a large-scale dataset from a real-world railway application demonstrate the usefulness of the approach, outperforming previous methods.
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。