VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911957839249408 |
|---|---|
| author | Qu, Zhen Tao, Xian Prasad, Mukesh Shen, Fei Zhang, Zhengtao Gong, Xinyi Ding, Guiguang |
| author_facet | Qu, Zhen Tao, Xian Prasad, Mukesh Shen, Fei Zhang, Zhengtao Gong, Xinyi Ding, Guiguang |
| contents | Recently, large-scale vision-language models such as CLIP have demonstrated immense potential in zero-shot anomaly segmentation (ZSAS) task, utilizing a unified model to directly detect anomalies on any unseen product with painstakingly crafted text prompts. However, existing methods often assume that the product category to be inspected is known, thus setting product-specific text prompts, which is difficult to achieve in the data privacy scenarios. Moreover, even the same type of product exhibits significant differences due to specific components and variations in the production process, posing significant challenges to the design of text prompts. In this end, we propose a visual context prompting model (VCP-CLIP) for ZSAS task based on CLIP. The insight behind VCP-CLIP is to employ visual context prompting to activate CLIP's anomalous semantic perception ability. In specific, we first design a Pre-VCP module to embed global visual information into the text prompt, thus eliminating the necessity for product-specific prompts. Then, we propose a novel Post-VCP module, that adjusts the text embeddings utilizing the fine-grained features of the images. In extensive experiments conducted on 10 real-world industrial anomaly segmentation datasets, VCP-CLIP achieved state-of-the-art performance in ZSAS task. The code is available at https://github.com/xiaozhen228/VCP-CLIP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12276 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation Qu, Zhen Tao, Xian Prasad, Mukesh Shen, Fei Zhang, Zhengtao Gong, Xinyi Ding, Guiguang Computer Vision and Pattern Recognition Recently, large-scale vision-language models such as CLIP have demonstrated immense potential in zero-shot anomaly segmentation (ZSAS) task, utilizing a unified model to directly detect anomalies on any unseen product with painstakingly crafted text prompts. However, existing methods often assume that the product category to be inspected is known, thus setting product-specific text prompts, which is difficult to achieve in the data privacy scenarios. Moreover, even the same type of product exhibits significant differences due to specific components and variations in the production process, posing significant challenges to the design of text prompts. In this end, we propose a visual context prompting model (VCP-CLIP) for ZSAS task based on CLIP. The insight behind VCP-CLIP is to employ visual context prompting to activate CLIP's anomalous semantic perception ability. In specific, we first design a Pre-VCP module to embed global visual information into the text prompt, thus eliminating the necessity for product-specific prompts. Then, we propose a novel Post-VCP module, that adjusts the text embeddings utilizing the fine-grained features of the images. In extensive experiments conducted on 10 real-world industrial anomaly segmentation datasets, VCP-CLIP achieved state-of-the-art performance in ZSAS task. The code is available at https://github.com/xiaozhen228/VCP-CLIP. |
| title | VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.12276 |