通过分布原型扩散学习，让正常样本更紧凑、异常样本更远离，提升开放集异常检测效果。
Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection
- 用可学习的高斯原型构建正常样本的紧凑分布空间
- 通过薛定谔桥实现正常样本向原型扩散，异常样本被排斥
- 在超球面学习分散特征，更好识别分布外异常，适合工业缺陷检测
在开放集监督异常检测（OSAD）中，现有方法通常生成伪异常样本以弥补真实异常样本不足，却忽视了正常样本的关键先验信息，导致判别边界不充分。为此，本文提出分布原型扩散学习（DPDL）方法，旨在将正常样本封闭于一个紧凑且具有区分性的分布空间中。具体而言，我们构建多个可学习的高斯原型，形成丰富的正常样本潜在表示空间，并学习一个薛定谔桥，促使正常样本向这些原型扩散，同时引导异常样本远离。此外，为增强样本间分离度，我们在超球面空间设计了一种分散特征学习机制，有助于识别分布外异常。实验结果表明，所提方法在9个公开数据集上均达到当前最优性能。
原文摘要 · Abstract (English)
In Open-set Supervised Anomaly Detection (OSAD), the existing methods typically generate pseudo anomalies to compensate for the scarcity of observed anomaly samples, while overlooking critical priors of normal samples, leading to less effective discriminative boundaries. To address this issue, we propose a Distribution Prototype Diffusion Learning (DPDL) method aimed at enclosing normal samples within a compact and discriminative distribution space. Specifically, we construct multiple learnable Gaussian prototypes to create a latent representation space for abundant and diverse normal samples and learn a Schrödinger bridge to facilitate a diffusive transition toward these prototypes for normal samples while steering anomaly samples away. Moreover, to enhance inter-sample separation, we design a dispersion feature learning way in hyperspherical space, which benefits the identification of out-of-distribution anomalies. Experimental results demonstrate the effectiveness and superiority of our proposed DPDL, achieving state-of-the-art performance on 9 public datasets.
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。