Diversity-Measurable Anomaly Detection
This work addresses a key bottleneck in anomaly detection for applications like surveillance and industrial inspection, offering an incremental improvement over existing methods.
The paper tackles the tradeoff problem in reconstruction-based anomaly detection where diverse normal patterns are poorly reconstructed, proposing the DMAD framework to enhance reconstruction diversity while avoiding generalization on anomalies. Experimental results on surveillance videos and industrial images demonstrate its effectiveness, including robustness to contaminated data and anomaly-like normal samples.
Reconstruction-based anomaly detection models achieve their purpose by suppressing the generalization ability for anomaly. However, diverse normal patterns are consequently not well reconstructed as well. Although some efforts have been made to alleviate this problem by modeling sample diversity, they suffer from shortcut learning due to undesired transmission of abnormal information. In this paper, to better handle the tradeoff problem, we propose Diversity-Measurable Anomaly Detection (DMAD) framework to enhance reconstruction diversity while avoid the undesired generalization on anomalies. To this end, we design Pyramid Deformation Module (PDM), which models diverse normals and measures the severity of anomaly by estimating multi-scale deformation fields from reconstructed reference to original input. Integrated with an information compression module, PDM essentially decouples deformation from prototypical embedding and makes the final anomaly score more reliable. Experimental results on both surveillance videos and industrial images demonstrate the effectiveness of our method. In addition, DMAD works equally well in front of contaminated data and anomaly-like normal samples.