发表机构
Korea University（高丽大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文揭示作物病害多模态分类的性能提升常源于会话泄漏，提出采用会话留出划分和无传感器基线来确保真实泛化。
AI 中文摘要
将环境传感器数据与叶片图像相结合被广泛报道可提高作物病害分类的准确性。在本工作中，我们揭示这些报道的增益往往是数据集构建的产物：因为单个传感器读数在单次会话（同一日期同一农场）中采集的许多图像之间共享，多模态网络可以通过记忆会话身份来预测病害。分析两个广泛使用的韩国数据集，即作物病害诊断（CDD）基准和AI Hub害虫/病害数据集，我们证明几乎所有图像共享传感器值，CDD测试图像中有91.9%在训练集中存在精确的传感器重复值。值得注意的是，仅给定时间戳的无图像分类器在所有七个评估作物上匹配或超过传感器驱动的预测，并匹配了最先进的CDD融合模型发表的宏观F1分数。这些结果表明，标准随机划分上的性能提升无法与会话泄漏区分开来。我们建议多模态作物研究必须在会话留出划分上进行评估，并报告与无传感器日期时间基线的对比性能，以确保真正的泛化。
英文摘要
Integrating environmental sensor data with leaf imagery is widely reported to boost crop disease classification accuracy. In this work, we reveal that these reported gains are often artifacts of dataset construction: because a single sensor reading is shared across many images collected in a single session (one farm on one date), multimodal networks can predict disease simply by memorizing session identities. Analyzing two widely used Korean datasets, the Crop Disease Diagnosis (CDD) benchmark and an AI Hub pest/disease dataset, we demonstrate that nearly all images share sensor values, with 91.9% of CDD test images having exact sensor duplicates in the training set. Remarkably, an image-free classifier given only timestamps matches or exceeds sensor-driven predictions across all seven evaluated crops, and matches the published macro-F1 of a state-of-the-art CDD fusion model. These results indicate that performance gains on standard random splits cannot be disentangled from session leakage. We propose that multimodal crop studies must evaluate on session-held-out splits and report performance against sensor-free date-time baselines to ensure genuine generalization.
