用轻量模型实现咖啡叶病智能诊断，省电又环保。
Energy-Aware Ensemble Learning for Coffee Leaf Disease Classification
- 用大模型知识蒸馏出小模型，再通过集成学习提升精度。
- 在受限设备上实现高准确率，能耗降低显著。
- 适合物联网场景，特别适用于偏远农田的可持续诊断。
咖啡产量依赖于疾病的及时准确诊断，但田间叶片疾病评估面临巨大挑战。尽管人工智能视觉模型可达到高精度，其应用受限于设备算力不足和网络连接不稳定。本研究通过知识蒸馏实现可持续的本地化诊断：在数据中心训练的大容量卷积神经网络（CNN）将知识传递给小型紧凑型CNN，结合集成学习（EL）优化。同时，通过简单且高效的密集微小模型对集成策略，提升准确率的同时严格遵守计算与能耗约束。在自建的咖啡叶病数据集上，经过蒸馏的小型集成模型表现媲美现有方法，但能耗和碳足迹大幅降低。结果表明，经恰当蒸馏与集成的小模型能为物联网（IoT）应用提供实用的诊断方案。
原文摘要 · Abstract (English)
Coffee yields are contingent on the timely and accurate diagnosis of diseases; however, assessing leaf diseases in the field presents significant challenges. Although Artificial Intelligence (AI) vision models achieve high accuracy, their adoption is hindered by the limitations of constrained devices and intermittent connectivity. This study aims to facilitate sustainable on-device diagnosis through knowledge distillation: high-capacity Convolutional Neural Networks (CNNs) trained in data centers transfer knowledge to compact CNNs through Ensemble Learning (EL). Furthermore, dense tiny pairs were integrated through simple and optimized ensembling to enhance accuracy while adhering to strict computational and energy constraints. On a curated coffee leaf dataset, distilled tiny ensembles achieved competitive with prior work with significantly reduced energy consumption and carbon footprint. This indicates that lightweight models, when properly distilled and ensembled, can provide practical diagnostic solutions for Internet of Things (IoT) applications.
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。