Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt

TL;DR

This paper introduces OneNIP, a novel method for multi-class anomaly detection that reconstructs normal features using only one normal image prompt, significantly improving detection and segmentation accuracy.

Contribution

The paper presents a new approach that enables anomaly detection and segmentation with just a single normal image prompt, enhancing efficiency and generalization over previous methods.

Findings

Outperforms previous methods on MVTec, BTAD, and VisA benchmarks.

Reconstructs anomalies effectively with only one normal image prompt.

Improves pixel-level anomaly segmentation with a supervised refiner.

Abstract

Unsupervised reconstruction networks using self-attention transformers have achieved state-of-the-art performance for multi-class (unified) anomaly detection with a single model. However, these self-attention reconstruction models primarily operate on target features, which may result in perfect reconstruction for both normal and anomaly features due to high consistency with context, leading to failure in detecting anomalies. Additionally, these models often produce inaccurate anomaly segmentation due to performing reconstruction in a low spatial resolution latent space. To enable reconstruction models enjoying high efficiency while enhancing their generalization for unified anomaly detection, we propose a simple yet effective method that reconstructs normal features and restores anomaly features with just One Normal Image Prompt (OneNIP). In contrast to previous work, OneNIP allows for the first time to reconstruct or restore anomalies with just one normal image prompt, effectively boosting unified anomaly detection performance. Furthermore, we propose a supervised refiner that regresses reconstruction errors by using both real normal and synthesized anomalous images, which significantly improves pixel-level anomaly segmentation. OneNIP outperforms previous methods on three industry anomaly detection benchmarks: MVTec, BTAD, and VisA. The code and pre-trained models are available at https://github.com/gaobb/OneNIP.