LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (4) · 4129-4137
DOI: 10.1609/aaai.v39i4.32433 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Er Jin und 6 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref).
Abstract (Originalsprache)
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 is critical for maintaining high-quality standards and minimizing costly recalls. Previous research in anomaly detection (AD) has relied on prior knowledge for designing algorithms, which often requires extensive manual annotations, 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 to 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 SOTA 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.
Zitieren
APA
Jin, E., Feng, Q., Mou, Y., Lakemeyer, G., Decker, S., Simons, O., & Stegmaier, J. (2025). LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 4129-4137. https://doi.org/10.1609/aaai.v39i4.32433
Vancouver
Jin E, Feng Q, Mou Y, Lakemeyer G, Decker S, Simons O, et al. LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(4):4129-4137. doi:10.1609/aaai.v39i4.32433
BibTeX
@article{Jin2025,
author = {Jin, Er and Feng, Qihui and Mou, Yongli and Lakemeyer, Gerhard and Decker, Stefan and Simons, Oliver and Stegmaier, Johannes},
title = {LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {4},
pages = {4129--4137},
doi = {10.1609/aaai.v39i4.32433}
}
EUVIMED