One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection

TL;DR

This paper introduces a personalized one-to-normal transformation and triplet contrastive inference to improve few-shot anomaly detection, demonstrating superior performance and transferability across multiple datasets and domains.

Contribution

The paper proposes a novel anomaly personalization method and a triplet contrastive inference strategy to enhance accuracy and robustness in few-shot anomaly detection.

Findings

Outperforms existing AD methods on eleven datasets

Enhances stability and robustness of anomaly detection

Improves other AD methods through generated data

Abstract

Traditional Anomaly Detection (AD) methods have predominantly relied on unsupervised learning from extensive normal data. Recent AD methods have evolved with the advent of large pre-trained vision-language models, enhancing few-shot anomaly detection capabilities. However, these latest AD methods still exhibit limitations in accuracy improvement. One contributing factor is their direct comparison of a query image's features with those of few-shot normal images. This direct comparison often leads to a loss of precision and complicates the extension of these techniques to more complex domains--an area that remains underexplored in a more refined and comprehensive manner. To address these limitations, we introduce the anomaly personalization method, which performs a personalized one-to-normal transformation of query images using an anomaly-free customized generation model, ensuring close alignment with the normal manifold. Moreover, to further enhance the stability and robustness of prediction results, we propose a triplet contrastive anomaly inference strategy, which incorporates a comprehensive comparison between the query and generated anomaly-free data pool and prompt information. Extensive evaluations across eleven datasets in three domains demonstrate our model's effectiveness compared to the latest AD methods. Additionally, our method has been proven to transfer flexibly to other AD methods, with the generated image data effectively improving the performance of other AD methods.