C3D-AD：基於可學習顧問的核注意力機制實現持續性3D異常檢測

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

August 2, 2025

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

cs.AI

摘要

三維異常檢測（3D Anomaly Detection, AD）在檢測高精度工業產品的異常或缺陷方面展現了巨大潛力。然而，現有方法通常以類別特定的方式進行訓練，且缺乏從新興類別中學習的能力。在本研究中，我們提出了一種名為持續三維異常檢測（Continual 3D Anomaly Detection, C3D-AD）的持續學習框架，該框架不僅能學習多類點雲的通用表示，還能處理隨時間出現的新類別。具體而言，在特徵提取模塊中，為了高效地從不同任務的多樣產品類型中提取通用局部特徵，引入了帶有隨機特徵層的核注意力（Kernel Attention with random feature Layer, KAL），該方法對特徵空間進行了標準化。接著，為了正確且持續地重建數據，提出了一種高效的帶有可學習顧問的核注意力（Kernel Attention with learnable Advisor, KAA）機制，該機制在編碼器和解碼器中學習新類別的信息，同時丟棄冗餘的舊信息。最後，為了保持任務間的表示一致性，提出了一種帶有參數擾動的重建（Reconstruction with Parameter Perturbation, RPP）模塊，通過設計表示排練損失函數，確保模型記住先前類別的信息並返回類別自適應的表示。在三個公開數據集上的廣泛實驗證明了所提方法的有效性，在Real3D-AD、Anomaly-ShapeNet和MulSen-AD上分別達到了66.4%、83.1%和63.4%的平均AUROC性能。

English

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.