LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction

Logical image understanding involves interpreting and reasoning about the relationships and consistency within an image's visual content. This capability is essential in applications such as industrial inspection, where logical anomaly detection (AD) is critical for maintaining high-quality standards and minimizing costly recalls. Previous research in AD has relied on prior knowledge for designing algorithms, which often requires extensive manual annotation effort, significant computing power, and large amounts of data for training. Autoregressive, multimodal Vision Language Models (AVLMs) offer a promising alternative due to their exceptional performance in visual reasoning across various domains. Despite this, their application in logical AD remains unexplored. In this work, we investigate using AVLMs for logical AD and demonstrate that they are well-suited to the task. Combining AVLMs with format embedding and a logic reasoner, we achieve state-of-the-art (SOTA) AD performance on public benchmarks, MVTec LOCO AD, with an AUROC of 86.0% and an F1-max of 83.7% along with explanations of the anomalies. This significantly outperforms the existing SOTA method by 18.1% in AUROC and 4.6% in F1-max score. The dataset, code and supplementary materials are available at https://jasonjin34.github.io/logicad.github.io/ .