Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning

[PDF] arxiv.org

On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes

S Ilyas, I Freeman, M Rottmann - arXiv preprint arXiv:2408.11221, 2024 - arxiv.org
Out-of-distribution (OOD) object detection is a critical task focused on detecting objects that
originate from a data distribution different from that of the training data. In this study, we …
相关文章 所有 2 个版本
[PDF] arxiv.org

AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2

S Damm, M Laszkiewicz, J Lederer… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advances in multimodal foundation models have set new standards in few-shot
anomaly detection. This paper explores whether high-quality visual features alone are …
相关文章 所有 2 个版本