发表机构
Institute of Information Science, Beijing Jiaotong University; Institute of Automation, Chinese Academy of Sciences（北京交通大学信息科学研究所; 中国科学院自动化研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有ZSAD方法可解释性与泛化性不足的问题，提出CoEvoAD协同进化框架，结合离散提示搜索与CCTO，在多数据集上实现ZSAD的SOTA性能。
AI 中文摘要
零样本异常检测（ZSAD）因在工业检测中的实用价值受到广泛关注。近期，基于CLIP的方法凭借强大的视觉-语言泛化能力被广泛应用于ZSAD。然而，现有方法通常采用连续提示嵌入进行提示优化，并在潜在向量中编码语义，这缺乏可解释性和可扩展性。为此，我们提出CoEvoAD，这是一个用于离散提示选择的协同进化框架。CoEvoAD使用进化算法在离散自然语言空间中执行提示搜索，在种群进化过程中迭代生成、评估和选择候选提示，从而保留自然语言的可解释性和可组合性。此外，我们引入跨类别迁移目标（CCTO），将保留的源类别作为未见类别的代理，并基于提示规则的估计跨类别迁移性对其进行评分，有效提升跨类别泛化能力。我们开展了大量实验验证CoEvoAD的有效性，结果显示其在多个异常检测数据集上达到了最先进的性能。代码可在该URL获取。
英文摘要
Zero-shot anomaly detection (ZSAD) has gained significant attention for its practical value in industrial inspection. Recently, CLIP-based approaches have been widely adopted in ZSAD due to their strong vision-language generalization capabilities. However, existing methods commonly employ continuous prompt embeddings for prompt optimization and encode semantics in latent vectors, which lack interpretability and scalability. To this end, we propose CoEvoAD, a co-evolutionary framework for discrete prompt selection. CoEvoAD performs prompt search in the discrete natural-language space using an evolutionary algorithm. Candidate prompts are iteratively generated, evaluated, and selected throughout population evolution, thus preserving the interpretability and composability of natural language. Furthermore, we introduce a Cross-Category Transfer Objective (CCTO), which treats held-out source categories as proxies for unseen categories and scores prompt rules based on their estimated cross-category transferability, effectively improving cross-category generalization. Extensive experiments are conducted to validate the effectiveness of CoEvoAD, and the results show that it achieves state-of-the-art performance across multiple anomaly detection datasets. The code is available at https://github.com/rstao-bjtu/CoEvoAD.
Comments25 pages, 25 figures. Camera-ready version. Accepted to EMNLP 2026 Main Conference
