农业 AI 落地常卡在域迁移上——不同果园的光照、品种会让模型失效。这篇用 CBAM 注意力+迁移学习把桃叶病害分类的跨域准确率拉到 93%，做作物病害检测的团队可以直接参考其微调策略。
研究者提出基于注意力机制和迁移学习的桃叶损伤分类方法，解决不同田间环境下的域迁移问题。他们构建了包含 1,366 张桃叶、6 类损伤的公开基准数据集，并评估多种深度学习架构。EfficientNetB5 结合 CBAM 注意力模块取得最佳准确率 93.3%，在少数类上表现更强。针对本地 180 张图像的域迁移测试，EfficientNetB3+CBAM 通过微调策略达到 93% 的宏 F1 分数，证明注意力机制能提升模型跨域泛化能力。
Attention mechanisms and transfer learning for robust peach leaf damage classification under domain shift
Artificial intelligence provides a practical framework for crop damage assessment from imagery data, supporting early decision-making in agricultural management. In peach orchards, climate change increases abiotic stress and biotic pressures, including pests and diseases, which often produce visually similar foliar symptoms. This overlap makes manual diagnosis difficult, especially across multiple fields with varying environmental conditions, highlighting the need for automated models with strong generalization ability. We propose an image-based classification approach for peach leaf damage detection. A benchmark dataset was created through manual annotation of publicly available images, consisting of 1,366 peach leaves across six damage categories. Several deep learning architectures were evaluated. EfficientNet models achieved the best results, with EfficientNetB0 reaching 92.9 percent accuracy, EfficientNetB3 achieving 91.5 percent, and EfficientNetB5 showing the strongest performance on minority classes. DenseNet121 reached 92.6 percent accuracy. The integration of the Convolutional Block Attention Module (CBAM) improved performance in several backbones, particularly EfficientNetB5 and InceptionV3, while showing limited or negative impact in others. The CBAM-enhanced EfficientNetB5 achieved the best overall accuracy of 93.3 percent. To evaluate robustness under realistic conditions, a local dataset of 180 images across four classes was collected, and transfer learning strategies were applied to address domain shift. Three fine-tuning strategies were tested. EfficientNetB3 combined with CBAM achieved the best performance in the local domain, reaching a 93 percent macro F1-score after transfer. Overall, attention-based models showed improved robustness for minority classes and better generalization across different field conditions.