AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
文献类型：会议论文
| 作者 | Zhaopeng Gu1,3 ; Bingke Zhu1,2; Guibo Zhu1,3; Yingying Chen1,2; Ming Tang1,3; Jinqiao Wang1,2,3
|
| 出版日期 | 2024-02-20 |
| 会议日期 | 2024-2-20至2024-2-27 |
| 会议地点 | VANCOUVER, CANADA |
| 英文摘要 | Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks. Despite their strong abilities in recognizing common objects due to extensive training datasets, they lack specifc domain knowledge and have a weaker understanding of localized details within objects, which hinders their effectiveness in the Industrial Anomaly Detection (IAD) task. On the other hand, most existing IAD methods only provide anomaly scores and necessitate the manual setting of thresholds to distinguish between normal and abnormal samples, which restricts their practical implementation. In this paper, we explore the utilization of LVLM to address the IAD problem and propose AnomalyGPT, a novel IAD approach based on LVLM. We generate training data by simulating anomalous images and producing corresponding textual descriptions for each image. We also employ an image decoder to provide
fne-grained semantic and design a prompt learner to finetune the LVLM using prompt embeddings. Our AnomalyGPT eliminates the need for manual threshold adjustments, thus directly assesses the presence and locations of anomalies. Additionally, AnomalyGPT supports multi-turn dialogues and
exhibits impressive few-shot in-context learning capabilities. With only one normal shot, AnomalyGPT achieves the state of-the-art performance with an accuracy of 86.1%, an image level AUC of 94.1%, and a pixel-level AUC of 95.3% on the MVTec-AD dataset. |
| 会议录出版者 | AAAI |
| 会议录出版地 | Menlo Park |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57293]  |
| 专题 | 紫东太初大模型研究中心 |
| 通讯作者 | Guibo Zhu; Yingying Chen |
| 作者单位 | 1.Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, 2.Objecteye Inc. 3.School of Artifcial Intelligence, University of Chinese Academy of Sciences |
| 推荐引用方式 GB/T 7714 | Zhaopeng Gu,Bingke Zhu,Guibo Zhu,et al. AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models[C]. 见:. VANCOUVER, CANADA. 2024-2-20至2024-2-27. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。