动态双流融合网络提升植物病害识别精度，尤其在小样本下表现优异。
DS_FusionNet: Dynamic Dual-Stream Fusion with Bidirectional Knowledge Distillation for Plant Disease Recognition
- 双主干网络+可变形动态融合，适应叶片遮挡与光照变化。
- 仅用10%数据即达90%以上准确率，复杂数据集仍保持85%精度。
- 适合农业智能诊断场景，对小样本病害识别有重要应用价值。
面对经济作物全球生长安全的严峻挑战，利用人工智能技术精准识别与预防植物病害已成为关键问题。针对小样本学习、叶片遮挡、光照变化及类别间高度相似性等技术难题，本研究提出动态双流融合网络（DS_FusionNet），集成双主干架构、可变形动态融合模块与双向知识蒸馏策略，显著提升识别准确率。实验表明，DS_FusionNet仅使用PlantDisease和CIFAR-10数据集的10%样本，分类准确率即超过90%，在复杂数据集PlantWild上仍保持85%准确率，展现出卓越的泛化能力。该研究为细粒度图像分类提供了新思路，也为农业病害的精准识别与管理奠定了坚实基础。
原文摘要 · Abstract (English)
Given the severe challenges confronting the global growth security of economic crops, precise identification and prevention of plant diseases has emerged as a critical issue in artificial intelligence-enabled agricultural technology. To address the technical challenges in plant disease recognition, including small-sample learning, leaf occlusion, illumination variations, and high inter-class similarity, this study innovatively proposes a Dynamic Dual-Stream Fusion Network (DS_FusionNet). The network integrates a dual-backbone architecture, deformable dynamic fusion modules, and bidirectional knowledge distillation strategy, significantly enhancing recognition accuracy. Experimental results demonstrate that DS_FusionNet achieves classification accuracies exceeding 90% using only 10% of the PlantDisease and CIFAR-10 datasets, while maintaining 85% accuracy on the complex PlantWild dataset, exhibiting exceptional generalization capabilities. This research not only provides novel technical insights for fine-grained image classification but also establishes a robust foundation for precise identification and management of agricultural diseases.
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。