SwinAD：用于无监督工业异常检测的多阶段特征重建

中文摘要 AI 辅助

工业异常检测旨在识别和定位缺陷区域，而无需依赖所有可能缺陷类型的详尽注释。尽管最近的无监督方法取得了不错的性能，但大多数主要针对单类设置，在多类场景中往往存在问题。本文提出SwinAD，一个基于重建的多类无监督异常检测框架，利用冻结的预训练Swin Transformer V2编码器和保持特征多样性的重建解码器。分层编码器提供语义丰富的多尺度特征，逐阶段瓶颈模块防止平凡恒等映射。为进一步改善定位，引入保持特征多样性的重建框架。在三个工业异常检测基准上的实验表明，SwinAD在图像级性能和像素级定位精度方面具有竞争力。

英文摘要

Industrial anomaly detection aims to identify and localize defective regions without relying on exhaustive annotations of all possible defect types. Although recent unsupervised methods have achieved strong performance, most are primarily designed for single-class settings and often struggle in multi-class scenarios, where diverse normal patterns may lead to over-generalization and reduce the discriminative capability between normal and anomalous regions. In this paper, we propose SwinAD, a reconstruction-based framework for multi-class unsupervised anomaly detection that leverages a frozen pretrained Swin Transformer V2 encoder and a feature diversity-preserving reconstruction decoder. The hierarchical encoder provides semantically rich multi-scale features, while stage-wise bottleneck modules with dropout prevent trivial identity mapping and encourage robust reconstruction of normal patterns. To further improve localization, we introduce a feature diversity-preserving reconstruction framework that maintains complementary reconstruction hypotheses instead of relying on a single decoding branch. The discrepancies between encoder features and the two reconstructed features are then aggregated across multiple scales to produce the final anomaly map. Experiments conducted on three industrial anomaly detection benchmarks, including MVTec AD, VisA, and Real-IAD, demonstrate that SwinAD achieves competitive image-level performance and strong pixel-level localization accuracy, with particularly notable improvements in pixel-level AP and 1 on MVTec AD. These results indicate that combining hierarchical Swin features with diverse multi-scale reconstruction substantially improve pixel-level localization in multi-class unsupervised anomaly setting.

发表机构

• Institute of Artificial Intelligence, University of Engineering and Technology, Vietnam National University（越南国立大学工程技术大学人工智能研究所）
• Human-Machine Interaction Laboratory, University of Engineering and Technology, Vietnam National University（越南国立大学工程技术大学人机交互实验室）
• Applied AI Lab, Phenikaa School of Computing, Phenikaa University（费尼卡大学计算学院应用人工智能实验室）

机构由 AI 辅助整理，请以论文原文为准。