Yan Tengfei, Tu Jiankai, Li Chunguang, Zhang Fan
IEEE Trans Neural Netw Learn Syst. 2025 Jun 23;PP. doi: 10.1109/TNNLS.2025.3579412.
Anomaly detection (AD) techniques are widely used in various fields. Existing techniques primarily focus on learning a normal region from single-view data, which may be not suitable for multiview data that provides more comprehensive information from multiple perspectives. Therefore, AD techniques designed for multiview data are necessary. Straightforwardly, one can concatenate the features learned from multiple single-view data into a joint representation to conduct AD. However, this may overlook the inevitable overlaps between views, potentially masking view-specific information due to the repetitive calculations of these overlaps. Among the various possible methods, one way to address this is to compress redundant information while maintaining comprehensive information across views. Following this way, in this article, we leverage the principle of information bottleneck (IB) to extract concise and comprehensive representations for multiview data. But it is problematic to directly use these representations for AD, since the multiview fusion process may disturb the intrinsic structure of the original data. That is, samples distributed at the edges/center of the original normal data distribution are mapped closer to the center/edges. This might cause abnormal samples (close to the normal data at the edges) to be incorrectly mapped into the normal region during inference. In the AD scenario, the absence of abnormal training samples makes it unfeasible to preserve this structure using supervised information. In this article, we design a topology-preserved regularization that unsupervisedly constrains the latent representations to preserve the original data's intrinsic structure, to improve the AD performance. Overall, we propose a topology-preserved multiview information bottleneck (TMVIB) feature extraction method to extract concise, comprehensive, and topology-preserved latent representations from multiview data. Interestingly, we find that the TMVIB feature extraction method itself can be viewed as a regularized anomaly detector, allowing it to output anomaly scores directly. Experiments on synthetic and real-world multiview datasets demonstrate the effectiveness of the proposed TMVIB.
异常检测（AD）技术在各个领域都有广泛应用。现有技术主要集中于从单视角数据中学习正常区域，这可能不适用于能从多个视角提供更全面信息的多视角数据。因此，设计用于多视角数据的AD技术是必要的。直观地说，可以将从多个单视角数据中学习到的特征连接成一个联合表示来进行AD。然而，这可能会忽略视角之间不可避免的重叠，由于这些重叠的重复计算，可能会掩盖特定视角的信息。在各种可能的方法中，一种解决此问题的方法是在保持跨视角全面信息的同时压缩冗余信息。按照这种方法，在本文中，我们利用信息瓶颈（IB）原理为多视角数据提取简洁而全面的表示。但直接将这些表示用于AD存在问题，因为多视角融合过程可能会干扰原始数据的内在结构。也就是说，分布在原始正常数据分布边缘/中心的样本会被映射得更靠近中心/边缘。这可能导致异常样本（在边缘处接近正常数据）在推理过程中被错误地映射到正常区域。在AD场景中，由于缺乏异常训练样本，使用监督信息来保留这种结构是不可行的。在本文中，我们设计了一种拓扑保持正则化方法，通过无监督地约束潜在表示来保留原始数据的内在结构，以提高AD性能。总体而言，我们提出了一种拓扑保持多视角信息瓶颈（TMVIB）特征提取方法，用于从多视角数据中提取简洁、全面且拓扑保持的潜在表示。有趣的是，我们发现TMVIB特征提取方法本身可以被视为一个正则化的异常检测器，使其能够直接输出异常分数。在合成和真实世界多视角数据集上的实验证明了所提出的TMVIB的有效性。
