arXiv 2603.079522026-03-09cs.CV

VisualAD: 通过视觉变换器实现无语言零样本异常检测

VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer

State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China（光电信息采集与防护技术国家重点实验室，安徽大学，合肥，中国）；School of Artificial Intelligence, Anhui University, Hefei, China（人工智能学院，安徽大学，合肥，中国）；College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China（智能科学与技术学院，国防科技大学，长沙，中国）

Yanning Hou, Peiyuan Li, Zirui Liu, Yitong Wang, Yanran Ruan, Jianfeng Qiu, Ke Xu

备注：: Accepted by CVPR 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

VisualAD通过纯视觉变换器实现无语言零样本异常检测，引入可学习标记和空间感知模块，提升异常检测性能。

摘要：

零样本异常检测（ZSAD）要求在没有目标类异常样本的情况下检测和定位异常。主流方法依赖于视觉-语言模型（VLMs）如CLIP：它们为正常和异常语义构建手工或学习的提示集，然后计算图像-文本相似性以实现开集判别。虽然有效，但这种范式依赖于文本编码器和跨模态对齐，可能导致训练不稳定和参数冗余。本工作重新审视ZSAD中文本分支的必要性，并提出VisualAD，一个纯视觉框架，基于视觉变换器。我们引入两个可学习的标记，嵌入在冻结的主干中，直接编码正常性和异常性。通过多层自注意力，这些标记与补丁标记相互作用，逐渐获得高层次的正常性和异常性概念，同时指导补丁突出异常相关线索。此外，我们还集成了空间感知交叉注意力（SCA）模块和轻量级自对齐函数（SAF）：SCA将细粒度的空间信息注入标记中，SAF在异常评分前重新校准补丁特征。VisualAD在13个零样本异常检测基准上实现了最先进的性能，涵盖工业和医疗领域，并能无缝适应预训练的视觉主干，如CLIP图像编码器和DINOv2。代码：https://github.com/7HHHHH/VisualAD

英文摘要：

Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VLMs) such as CLIP: they build hand-crafted or learned prompt sets for normal and abnormal semantics, then compute image-text similarities for open-set discrimination. While effective, this paradigm depends on a text encoder and cross-modal alignment, which can lead to training instability and parameter redundancy. This work revisits the necessity of the text branch in ZSAD and presents VisualAD, a purely visual framework built on Vision Transformers. We introduce two learnable tokens within a frozen backbone to directly encode normality and abnormality. Through multi-layer self-attention, these tokens interact with patch tokens, gradually acquiring high-level notions of normality and anomaly while guiding patches to highlight anomaly-related cues. Additionally, we incorporate a Spatial-Aware Cross-Attention (SCA) module and a lightweight Self-Alignment Function (SAF): SCA injects fine-grained spatial information into the tokens, and SAF recalibrates patch features before anomaly scoring. VisualAD achieves state-of-the-art performance on 13 zero-shot anomaly detection benchmarks spanning industrial and medical domains, and adapts seamlessly to pretrained vision backbones such as the CLIP image encoder and DINOv2. Code: https://github.com/7HHHHH/VisualAD

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。