利用光吸收定律指导学习，提升太赫兹食品检测中异常识别能力
Beer-Lambert Guided Representation Learning for Unsupervised Anomaly Detection in Sub-THz Food Inspection Images
- 基于比尔-朗伯定律设计衰减分解模块，约束特征学习过程
- 在真实数据集上实现优于基线方法的异常检测性能
- 适用于未见过食物类别的泛化测试，适合工业质检场景
食品制造需要可靠的检测系统来识别异物污染并保障产品安全。太赫兹透射成像能提供与材料相关的衰减特性，有助于检测食品中的低密度异物。然而，现有无监督异常检测方法主要依赖于RGB预训练视觉表征，可能无法充分捕捉太赫兹图像的传输行为。本文提出一种基于比尔-朗伯定律的无监督异常检测表征学习框架。所提方法引入衰减分解模块作为辅助正则化模块，在训练过程中通过衰减重建约束学生模型的表示。除传统单类设置外，还引入了“留一食品”评估协议，以检验在未见食物类别下的泛化能力。在Inline-Food-Inspection-THz数据集上的实验结果表明，该方法在整体异常检测性能上优于基线方法。
原文摘要 · Abstract (English)
Food manufacturing requires reliable inspection systems to detect foreign material contamination and maintain product safety. Sub-THz transmission imaging provides material-dependent attenuation characteristics that are useful for detecting low-density contaminants in food products. However, existing unsupervised anomaly detection methods mainly rely on RGB-pretrained visual representations, which may not adequately capture the transmission behavior of Sub-THz images. This paper proposes a Beer-Lambert guided representation learning framework for unsupervised anomaly detection in Sub-THz food inspection images. The proposed method introduces an attenuation decomposition module as an auxiliary regularization module that constrains student representations through attenuation reconstruction during training. In addition to the conventional one-class setting, we introduce a Leave-One-Food-Out protocol to evaluate generalization capability under unseen food categories. Experimental results on the Inline-Food-Inspection-THz dataset show that the proposed method improves overall anomaly detection performance over the baseline method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。