Anomaly Detection by Adapting a pre-trained Vision Language Model
This addresses the need for efficient anomaly detection in industrial settings, though it is incremental as it builds on existing CLIP models.
The paper tackles the problem of anomaly detection in industrial images by adapting a pre-trained CLIP model, achieving state-of-the-art results of 97.5/55.6 on MVTec-AD and 89.3/33.1 on VisA for detection and localization.
Recently, large vision and language models have shown their success when adapting them to many downstream tasks. In this paper, we present a unified framework named CLIP-ADA for Anomaly Detection by Adapting a pre-trained CLIP model. To this end, we make two important improvements: 1) To acquire unified anomaly detection across industrial images of multiple categories, we introduce the learnable prompt and propose to associate it with abnormal patterns through self-supervised learning. 2) To fully exploit the representation power of CLIP, we introduce an anomaly region refinement strategy to refine the localization quality. During testing, the anomalies are localized by directly calculating the similarity between the representation of the learnable prompt and the image. Comprehensive experiments demonstrate the superiority of our framework, e.g., we achieve the state-of-the-art 97.5/55.6 and 89.3/33.1 on MVTec-AD and VisA for anomaly detection and localization. In addition, the proposed method also achieves encouraging performance with marginal training data, which is more challenging.