arXiv 2508.013112025-08-02cs.CVcs.LG

C3D-AD：通过具有可学习顾问的内核注意力实现持续3D异常检测

C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

Haoquan Lu, Hanzhe Liang, Jie Zhang, Chenxi Hu, Jinbao Wang, Can Gao

备注：: We have provided the code for C3D-AD with checkpoints and BASELINE at this link: https://github.com/hzzzzzhappy/CL3AD

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出持续3D异常检测框架C3D-AD，通过内核注意力与可学习顾问机制，实现多类别点云泛化表示及新类别持续学习，在三个数据集上取得优异AUROC。

摘要：

3D异常检测（AD）在高精度工业产品的异常或缺陷检测方面展现出巨大潜力。然而，现有方法通常以类别特定的方式进行训练，并且缺乏从新兴类别中学习的能力。在本研究中，我们提出了一种名为持续3D异常检测（C3D-AD）的持续学习框架，它不仅能为多类别点云学习泛化表示，还能处理随时间出现的新类别。具体而言，在特征提取模块中，为了高效地从不同任务的不同产品类型中提取泛化的局部特征，引入了具有随机特征层的内核注意力（KAL），该机制对特征空间进行归一化。然后，为了正确且持续地重建数据，提出了一种具有可学习顾问的高效内核注意力（KAA）机制，该机制在编码器和解码器中学习新类别的信息，同时丢弃冗余的旧信息。最后，为了保持任务间的表示一致性，通过设计一种表示排练损失函数，提出了参数扰动重建（RPP）模块，该模块确保模型记住先前的类别信息并返回类别自适应的表示。在三个公开数据集上进行的大量实验证明了所提方法的有效性，在Real3D-AD、Anomaly-ShapeNet和MulSen-AD上分别实现了66.4%、83.1%和63.4%的平均AUROC。

英文摘要：

3D Anomaly Detection (AD) has shown great potential in detecting anomalies or defects of high-precision industrial products. However, existing methods are typically trained in a class-specific manner and also lack the capability of learning from emerging classes. In this study, we proposed a continual learning framework named Continual 3D Anomaly Detection (C3D-AD), which can not only learn generalized representations for multi-class point clouds but also handle new classes emerging over time.Specifically, in the feature extraction module, to extract generalized local features from diverse product types of different tasks efficiently, Kernel Attention with random feature Layer (KAL) is introduced, which normalizes the feature space. Then, to reconstruct data correctly and continually, an efficient Kernel Attention with learnable Advisor (KAA) mechanism is proposed, which learns the information from new categories while discarding redundant old information within both the encoder and decoder. Finally, to keep the representation consistency over tasks, a Reconstruction with Parameter Perturbation (RPP) module is proposed by designing a representation rehearsal loss function, which ensures that the model remembers previous category information and returns category-adaptive representation.Extensive experiments on three public datasets demonstrate the effectiveness of the proposed method, achieving an average performance of 66.4%, 83.1%, and 63.4% AUROC on Real3D-AD, Anomaly-ShapeNet, and MulSen-AD, respectively.

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。