{"ID":2886362,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.03447","arxiv_id":"2508.03447","title":"CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection","abstract":"Recently, large pre-trained vision-language models have shown remarkable performance in zero-shot anomaly detection (ZSAD). With fine-tuning on a single auxiliary dataset, the model enables cross-category anomaly detection on diverse datasets covering industrial defects and medical lesions. Compared to manually designed prompts, prompt learning eliminates the need for expert knowledge and trial-and-error. However, it still faces the following challenges: (i) static learnable tokens struggle to capture the continuous and diverse patterns of normal and anomalous states, limiting generalization to unseen categories; (ii) fixed textual labels provide overly sparse category information, making the model prone to overfitting to a specific semantic subspace. To address these issues, we propose Conditional Prompt Synthesis (CoPS), a novel framework that synthesizes dynamic prompts conditioned on visual features to enhance ZSAD performance. Specifically, we extract representative normal and anomaly prototypes from fine-grained patch features and explicitly inject them into prompts, enabling adaptive state modeling. Given the sparsity of class labels, we leverage a variational autoencoder to model semantic image features and implicitly fuse varied class tokens into prompts. Additionally, integrated with our spatially-aware alignment mechanism, extensive experiments demonstrate that CoPS surpasses state-of-the-art methods by 1.4% in classification AUROC and 1.9% in segmentation AUROC across 13 industrial and medical datasets. The code is available at https://github.com/cqylunlun/CoPS.","short_abstract":"Recently, large pre-trained vision-language models have shown remarkable performance in zero-shot anomaly detection (ZSAD). With fine-tuning on a single auxiliary dataset, the model enables cross-category anomaly detection on diverse datasets covering industrial defects and medical lesions. Compared to manually designe...","url_abs":"https://arxiv.org/abs/2508.03447","url_pdf":"https://arxiv.org/pdf/2508.03447v2","authors":"[\"Qiyu Chen\",\"Zhen Qu\",\"Wei Luo\",\"Haiming Yao\",\"Yunkang Cao\",\"Yuxin Jiang\",\"Yinan Duan\",\"Huiyuan Luo\",\"Chengkan Lv\",\"Zhengtao Zhang\"]","published":"2025-08-05T13:47:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":611302,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2886362,"paper_url":"https://arxiv.org/abs/2508.03447","paper_title":"CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection","repo_url":"https://github.com/cqylunlun/CoPS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}