arXiv 2606.297142026-06-29cs.CV

UniVAD v2: 基于支持条件边界构建的统一视觉异常检测

UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction

Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Yinwang Intelligent Technology Co. Ltd.（银河智能科技有限公司）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Wuhan AI Research（武汉人工智能研究所）；Peng Cheng Laboratory（鹏城实验室）；Guangdong Provincial Key Laboratory of Intellectual Property & Big Data（广东省知识产权与大数据重点实验室）

Zhaopeng Gu, Bingke Zhu, Zhaowen Li, Guibo Zhu, Yingying Chen, Ming Tang, Peng Su, Jinqiao Wang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出UniVAD v2框架，通过最优传输关系建模、自适应协调机制和少样本异常参考模块，在统一视觉异常检测中实现跨类别、跨域泛化，提升检测性能。

摘要：

统一视觉异常检测旨在训练一个可跨类别、跨域和应用场景部署的单一检测器。在少样本迁移场景中，关键挑战是从少量支持集为未见过的目标类别估计一个情节特定的边界。现有方法主要从正常侧证据推断该边界，并为部署特定的容错提供有限的异常侧证据。在正常侧，它们往往难以联合捕获局部对应关系和全局支持-查询关系，使得其边界对未见异常不够可靠。为解决这些问题，我们提出UniVAD v2，一个双面支持条件边界构建框架，用于统一视觉异常检测。基于UniVAD的组件-补丁分治框架，UniVAD v2通过最优传输关系建模模块（OTRM）增强正常侧，该模块通过传输式分配用支持-查询匹配补充检索；以及检索与关系建模自适应协调机制（ACRRM），该机制估计情节条件可靠性以融合两种证据源。在异常侧，少样本异常参考模块（FAR）将可选的异常参考转换为拒绝侧证据用于边界调整。在涵盖工业、逻辑和医学异常检测的六个数据集上的实验证明了强跨域泛化能力。在1N-shot协议下，UniVAD v2将平均图像级AUC从UniVAD的83.0%提升至84.5%，并在1N+1A-shot设置下进一步达到85.7%。在MVTec-AD严重性分割（MVTec-AD-SS）上，UniVAD v2实现了96.2%的图像级AUC和96.9%的像素级AUC，表明异常参考无需重新训练即可实现可控边界定制。

英文摘要：

Unified visual anomaly detection seeks to train a single detector that can be deployed across categories, domains, and application scenarios. In the few-shot transfer regime, the key challenge is to estimate an episode-specific boundary for an unseen target category from a small support set. Existing approaches mainly infer this boundary from normal-side evidence and provide limited abnormal-side evidence for deployment-specific tolerance. Within the normal side, they often struggle to jointly capture local correspondences and global support-query relations, making their boundaries less reliable for unseen anomalies. To address these issues, we propose UniVAD v2, a two-sided support-conditioned boundary construction framework for unified visual anomaly detection. Built on the component-patch divide-and-conquer framework of UniVAD, UniVAD v2 strengthens the normal side with an Optimal Transport-based Relational Modeling module (OTRM), which complements retrieval with support-query matching through transport-style allocation, and an Adaptive Coordination mechanism for Retrieval and Relational Modeling (ACRRM), which estimates episode-conditioned reliabilities to fuse the two sources of evidence. On the abnormal side, a Few-Shot Abnormal Reference module (FAR) converts optional abnormal references into rejection-side evidence for boundary adjustment. Experiments on six datasets spanning industrial, logical, and medical anomaly detection demonstrate strong cross-domain generalization. Under the 1N-shot protocol, UniVAD v2 improves the mean image-level AUC over UniVAD from 83.0\% to 84.5\%, and further reaches 85.7\% in the 1N+1A-shot setting. On the MVTec-AD Severity Split (MVTec-AD-SS), UniVAD v2 achieves 96.2\% image-level AUC and 96.9\% pixel-level AUC, showing that abnormal references enable controllable boundary customization without retraining.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。