Papers › VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation

VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation

17 Jul 2024arXiv:2407.12276archive 2025-07-28

Zhen Qu, Xian Tao, Mukesh Prasad, Fei Shen, Zhengtao Zhang, Xinyi Gong, Guiguang Ding

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.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xiaozhen228/vcp-clip officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly Detection Anomaly Segmentation Zero Shot Segmentation zero-shot anomaly detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Anomaly Detection	MVTec AD	VCP-CLIP	Segmentation AP	49.4	#131 of 148	Archive leaderboard	report
Anomaly Detection	MVTec AD	VCP-CLIP	Segmentation AUPRO	87.3	#131 of 148	Archive leaderboard	report
Anomaly Detection	MVTec AD	VCP-CLIP	Segmentation AUROC	92.0	#131 of 148	Archive leaderboard	report
Anomaly Detection	VisA	VCP-CLIP	Segmentation AUPRO	90.7	#50 of 50	Archive leaderboard	report
Anomaly Detection	VisA	VCP-CLIP	Segmentation AUROC	95.7	#50 of 50	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections