零样本图像异常检测的自动提示生成与定位目标检测
Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection
AI总结：
针对工业产品缺陷检测的传统人工方法问题，提出基于GPT-3、Grounding DINO和CLIP三个基础模型的零样本无训练多模态方法，在MVTec-AD和VisA数据集上实现高精度检测，为工业制造提供高效质量控制方案。
摘要：
识别工业产品中的缺陷和异常是一项关键的质量控制任务。传统的人工检测方法速度慢、主观且容易出错。在这项工作中，我们提出了一种新颖的零样本无训练方法，通过包含三个基础模型的多模态机器学习管道实现自动化工业图像异常检测。我们的方法首先使用大型语言模型（即GPT-3）生成描述正常和异常产品预期外观的文本提示。然后，我们使用名为Grounding DINO的定位目标检测模型在图像中定位产品。最后，我们使用名为CLIP的零样本图像-文本匹配模型将裁剪后的产品图像块与生成的提示进行比较，以识别任何异常。我们在两个工业产品图像数据集（即MVTec-AD和VisA）上的实验证明了该方法的有效性，无需模型训练即可在检测各种类型的缺陷和异常时实现高精度。我们提出的模型能够在工业制造环境中实现高效、可扩展且客观的质量控制。
英文摘要：
Identifying defects and anomalies in industrial products is a critical quality control task. Traditional manual inspection methods are slow, subjective, and error-prone. In this work, we propose a novel zero-shot training-free approach for automated industrial image anomaly detection using a multimodal machine learning pipeline, consisting of three foundation models. Our method first uses a large language model, i.e., GPT-3. generate text prompts describing the expected appearances of normal and abnormal products. We then use a grounding object detection model, called Grounding DINO, to locate the product in the image. Finally, we compare the cropped product image patches to the generated prompts using a zero-shot image-text matching model, called CLIP, to identify any anomalies. Our experiments on two datasets of industrial product images, namely MVTec-AD and VisA, demonstrate the effectiveness of this method, achieving high accuracy in detecting various types of defects and anomalies without the need for model training. Our proposed model enables efficient, scalable, and objective quality control in industrial manufacturing settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
