域偏移下基于注意力机制和迁移学习的鲁棒桃叶损伤分类
Quantifying and Mitigating Domain Shift in Peach Leaf Damage Classification: Attention Mechanisms and Fine-Tuning Strategies
AI总结:
提出基于注意力机制和迁移学习的桃叶损伤分类方法,通过CBAM增强EfficientNet模型在公共数据集上达到93.3%准确率,并在本地数据集上通过迁移学习实现93%宏F1分数,有效应对域偏移。
摘要:
人工智能为从图像数据评估作物损伤提供了实用框架,支持农业管理中的早期决策。在桃园中,气候变化增加了非生物胁迫和生物压力,包括病虫害,这些通常产生视觉上相似的叶片症状。这种重叠使得手动诊断变得困难,尤其是在不同环境条件下的多个田地中,凸显了对具有强泛化能力的自动化模型的需求。 我们提出了一种基于图像的桃叶损伤检测分类方法。通过手动标注公开图像创建了一个基准数据集,包含六个损伤类别的1,366片桃叶。评估了几种深度学习架构。EfficientNet模型取得了最佳结果,其中EfficientNetB0达到92.9%的准确率,EfficientNetB3达到91.5%,EfficientNetB5在少数类上表现最强。DenseNet121达到92.6%的准确率。卷积块注意力模块(CBAM)的集成在多个骨干网络中提升了性能,特别是在EfficientNetB5和InceptionV3中,而在其他网络中效果有限或为负。CBAM增强的EfficientNetB5取得了93.3%的最佳总体准确率。 为了评估在现实条件下的鲁棒性,收集了一个包含四个类别180张图像的本地数据集,并应用迁移学习策略来解决域偏移。测试了三种微调策略。结合CBAM的EfficientNetB3在本地域中取得了最佳性能,迁移后宏F1分数达到93%。总体而言,基于注意力的模型在少数类上表现出更强的鲁棒性,并在不同田间条件下具有更好的泛化能力。
英文摘要:
Deep learning models for crop damage assessment are typically trained and validated on curated public imagery, yet their behaviour when deployed in real orchards remains poorly quantified. This work measures and mitigates that gap for peach leaf damage classification, where climate-driven abiotic and biotic stresses produce visually similar foliar symptoms. A benchmark of 1366 manually annotated peach leaves covering six damage types was assembled from public sources, and a second, independently acquired dataset of 180 field images across four classes was collected in a commercial orchard as an unseen target domain. Eleven convolutional backbones and three attention-enhanced variants were compared; CBAM-EfficientNetB5 achieved the best source-domain performance (93.3\% accuracy, 0.849 macro F1). Applied directly to the target domain, source-trained models lost on average 0.21 macro F1 points (26.5\% relative), with 12 of 14 architectures degrading, confirming that benchmark performance substantially overestimates field behaviour. Three fine-tuning strategies were then evaluated as mitigation: feature extraction proved insufficient in nearly all cases, whereas full fine-tuning recovered performance, with CBAM-EfficientNetB3 reaching 0.9459 accuracy and 0.9297 macro F1 on the local domain. Attention mechanisms improved minority-class recall and adaptation efficiency, but did not by themselves confer robustness to domain shift. The results establish a transferability baseline for peach leaf diagnosis and quantify the adaptation cost of moving from public benchmarks to operational orchards.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。