Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization

TL;DR

This paper introduces ADClick, an interactive segmentation algorithm that efficiently generates high-quality anomaly masks with minimal manual clicks, improving industrial anomaly detection and localization while reducing labeling costs.

Contribution

The paper presents ADClick, a novel interactive segmentation method that significantly enhances anomaly mask generation with minimal annotations, and extends it to ADClick-Seg for improved detection and localization.

Findings

ADClick achieves 94.1% AP on MVTec AD with only 3-5 clicks per image.

ADClick-Seg outperforms previous methods with 86.4% AP on MVTec AD.

The approach reduces labeling effort while maintaining high detection accuracy.

Abstract

In the realm of practical Anomaly Detection (AD) tasks, manual labeling of anomalous pixels proves to be a costly endeavor. Consequently, many AD methods are crafted as one-class classifiers, tailored for training sets completely devoid of anomalies, ensuring a more cost-effective approach. While some pioneering work has demonstrated heightened AD accuracy by incorporating real anomaly samples in training, this enhancement comes at the price of labor-intensive labeling processes. This paper strikes the balance between AD accuracy and labeling expenses by introducing ADClick, a novel Interactive Image Segmentation (IIS) algorithm. ADClick efficiently generates "ground-truth" anomaly masks for real defective images, leveraging innovative residual features and meticulously crafted language prompts. Notably, ADClick showcases a significantly elevated generalization capacity compared to existing state-of-the-art IIS approaches. Functioning as an anomaly labeling tool, ADClick generates high-quality anomaly labels (AP $= 94.1\%$ on MVTec AD) based on only $3$ to $5$ manual click annotations per training image. Furthermore, we extend the capabilities of ADClick into ADClick-Seg, an enhanced model designed for anomaly detection and localization. By fine-tuning the ADClick-Seg model using the weak labels inferred by ADClick, we establish the state-of-the-art performances in supervised AD tasks (AP $= 86.4\%$ on MVTec AD and AP $= 78.4\%$, PRO $= 98.6\%$ on KSDD2).