用双流网络实时无损评估油炸油氧化，精度超98%。
FryNet: Dual-Stream Adversarial Fusion for Non-Destructive Frying Oil Oxidation Assessment
- 双流结构融合可见光与热成像，联合分割、分类与化学指标回归
- 在28段视频上实现98.97%分割精度和100%分类准确率
- 解决传感器噪声干扰问题，适合工业实时监测场景
油炸油劣化监测对食品安全至关重要，但现有方法依赖破坏性湿化学分析，无法提供空间信息且不适用于实时检测。我们识别出基于热成像的检测中一个根本障碍——相机指纹捷径，即模型记忆传感器特异性噪声和热偏移而非学习氧化化学机制，在视频间测试时性能崩溃。为此提出FryNet，一种双流RGB-热成像框架，可在一次前向传播中同时完成油区分割、可用性分类及四个化学氧化指标（PV, p-AV, Totox, 温度）的回归。采用ThermalMiT-B2主干提取热特征，结合通道与空间注意力；RGB-MAE编码器通过掩码自编码与化学对齐学习化学相关表示。双编码器DANN通过梯度反转层对抗视频身份干扰，FiLM融合桥接热结构与可见光化学上下文。在28段油炸视频共7,226对帧上，FryNet达到98.97% mIoU、100%分类准确率和2.32平均回归MAE，优于全部七种基线方法。
原文摘要 · Abstract (English)
Monitoring frying oil degradation is critical for food safety, yet current practice relies on destructive wet-chemistry assays that provide no spatial information and are unsuitable for real-time use. We identify a fundamental obstacle in thermal-image-based inspection, the camera-fingerprint shortcut, whereby models memorize sensor-specific noise and thermal bias instead of learning oxidation chemistry, collapsing under video-disjoint evaluation. We propose FryNet, a dual-stream RGB-thermal framework that jointly performs oil-region segmentation, serviceability classification, and regression of four chemical oxidation indices (PV, p-AV, Totox, temperature) in a single forward pass. A ThermalMiT-B2 backbone with channel and spatial attention extracts thermal features, while an RGB-MAE Encoder learns chemically grounded representations via masked autoencoding and chemical alignment. Dual-Encoder DANN adversarially regularizes both streams against video identity via Gradient Reversal Layers, and FiLM fusion bridges thermal structure with RGB chemical context. On 7,226 paired frames across 28 frying videos, FryNet achieves 98.97% mIoU, 100% classification accuracy, and 2.32 mean regression MAE, outperforming all seven baselines.
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。