arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.22874cs.CV

基于模板的特征聚合网络用于工业异常检测

Template-Based Feature Aggregation Network for Industrial Anomaly Detection

State Key Laboratory of Precision Measurement Technology and Instruments（精密测量技术与仪器国家重点实验室）；Tsinghua University（清华大学）；State Key Laboratory of Digital Manufacturing Equipment and Technology（数字制造装备与技术国家重点实验室）；Huazhong University of Science and Technology（华中科技大学）

Wei Luo, Haiming Yao, Wenyong Yu

备注：
Accepted by Engineering Applications of Artificial Intelligence
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出TFA-Net，通过模板特征聚合过滤异常特征，提升工业异常检测性能，实现高效率和实时性。

摘要：

工业异常检测在确保产品质量控制中起着关键作用。因此，提出有效的异常检测模型具有重要意义。尽管现有特征重建方法表现出色，但它们面临捷径学习的挑战，可能导致异常特征的不可接受重建。为此，我们提出了一种新的特征重建模型，称为基于模板的特征聚合网络（TFA-Net），用于通过模板基于的特征聚合进行异常检测。具体而言，TFA-Net首先从预训练的卷积神经网络中提取多个层次特征，用于固定模板图像和输入图像。与直接重建输入特征不同，TFA-Net将它们聚合到模板特征上，有效过滤出与正常模板特征相似性低的异常特征。接下来，TFA-Net利用已经融合了输入特征中正常特征的模板特征来细化特征并获得重建的特征图。最后，通过比较输入和重建特征的差异来定位缺陷区域。此外，采用随机遮蔽策略对输入特征进行增强，以提高模型的整体检查性能。我们的基于模板的特征聚合方案产生了一个非平凡且有意义的特征重建任务。简单的、高效的TFA-Net在各种现实工业数据集上表现出最先进的检测性能。此外，它满足了工业场景的实时需求，使其在实际应用中具有高度的适用性。代码可在https://github.com/luow23/TFA-Net上获取。

英文摘要：

Industrial anomaly detection plays a crucial role in ensuring product quality control. Therefore, proposing an effective anomaly detection model is of great significance. While existing feature-reconstruction methods have demonstrated excellent performance, they face challenges with shortcut learning, which can lead to undesirable reconstruction of anomalous features. To address this concern, we present a novel feature-reconstruction model called the \textbf{T}emplate-based \textbf{F}eature \textbf{A}ggregation \textbf{Net}work (TFA-Net) for anomaly detection via template-based feature aggregation. Specifically, TFA-Net first extracts multiple hierarchical features from a pre-trained convolutional neural network for a fixed template image and an input image. Instead of directly reconstructing input features, TFA-Net aggregates them onto the template features, effectively filtering out anomalous features that exhibit low similarity to normal template features. Next, TFA-Net utilizes the template features that have already fused normal features in the input features to refine feature details and obtain the reconstructed feature map. Finally, the defective regions can be located by comparing the differences between the input and reconstructed features. Additionally, a random masking strategy for input features is employed to enhance the overall inspection performance of the model. Our template-based feature aggregation schema yields a nontrivial and meaningful feature reconstruction task. The simple, yet efficient, TFA-Net exhibits state-of-the-art detection performance on various real-world industrial datasets. Additionally, it fulfills the real-time demands of industrial scenarios, rendering it highly suitable for practical applications in the industry. Code is available at https://github.com/luow23/TFA-Net.

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。

↑