[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2502":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"view_count":31,"doi":32,"paper":33,"created_at":48},2502,"CBAM-LeafGAN: A selective attention-guided StyleGAN framework for mango leaf disease image synthesis and explainable recognition","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112409","The development of robust deep learning systems for plant disease diagnosis is constrained by limited expert-annotated datasets, class imbalance, and insufficient visual diversity, particularly in real-world field mango leaf disease classification. To address these challenges, this paper proposes CBAM-LeafGAN, a Selective Residual-Gated CBAM-enhanced StyleGAN3-t framework for disease-specific image synthesis and augmentation. Lightweight Residual-Gated Convolutional Block Attention Modules are selectively integrated into the intermediate synthesis layers to enhance disease-relevant feature generation while preserving alias-free synthesis. Evaluated on the MangoLeafDS2025 dataset, CBAM-LeafGAN was compared with StyleGAN3-t, StyleGAN3-r, Vanilla Latent Diffusion Model, DiffusionPix2Pix, Variational Autoencoder, and LeafGAN. It achieved the lowest Fréchet Inception Distance (FID) of 12.44 among the evaluated models. Ablation, t-SNE, nearest-neighbour diversity, Turing tests, and statistical analyses further validated the realism and diversity of the images. Synthetic augmentation improved disease classification across 23 deep learning architectures and mitigated class imbalance. Evaluation of the proposed approach on the comparable dataset MangoLeafBD further demonstrated improved performance over state-of-the-art methods. Grad-CAM visualisation and quantitative explainability analysis confirmed the consistent localisation of disease-relevant regions, supporting the reliability and interpretability of the proposed framework for mango leaf disease diagnosis under data-constrained agricultural conditions and indicating its potential for practical field deployment.","为植物病害诊断构建稳健的深度学习系统受到专家标注数据集有限、类别不平衡以及视觉多样性不足的制约，尤其是在真实田间芒果叶片病害分类场景中。为应对这些挑战，本文提出CBAM-LeafGAN，一种用于病害特异性图像合成与增强的选择性残差门控CBAM增强StyleGAN3-t框架。轻量级残差门控卷积块注意力模块（Residual-Gated Convolutional Block Attention Modules）被选择性地集成到中间合成层中，以增强病害相关特征的生成，同时保持无混叠合成。在MangoLeafDS2025数据集上进行评估时，CBAM-LeafGAN与StyleGAN3-t、StyleGAN3-r、原始潜在扩散模型（Vanilla Latent Diffusion Model）、DiffusionPix2Pix、变分自编码器（Variational Autoencoder）和LeafGAN进行了比较。在受评估模型中，它取得了最低的Fréchet Inception距离（FID），为12.44。消融实验、t-SNE、最近邻多样性、图灵测试和统计分析进一步验证了图像的真实性和多样性。合成增强在23种深度学习架构上改善了病害分类，并缓解了类别不平衡。在可比数据集MangoLeafBD上对所提方法进行评估，进一步证明其性能优于当前最先进方法。Grad-CAM可视化和定量可解释性分析证实了病害相关区域定位的一致性，支持了所提框架在数据受限农业条件下用于芒果叶片病害诊断的可靠性和可解释性，并表明其在实际田间部署中的潜力。",null,"Computers and Electronics in Agriculture","2026-09-14T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"提出CBAM-LeafGAN生成式数据增强框架，在芒果叶病害识别上取得FID 12.44并提升23种模型分类性能，方法新颖、验证充分，对数据受限场景下的作物病害智能诊断有参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","芒果","病害识别","图像合成",0,"10.1016\u002Fj.compag.2026.112409",{"doi":32,"openalex_id":34,"authors":35,"venue":10,"cited_by_count":31,"oa_url":6,"card":41,"direction":45,"ingested_from":47},"W7212973113",[36,38],{"name":37,"orcid":9},"Pankajkumar Thakre",{"name":39,"orcid":40},"Jagdish Chakole","https:\u002F\u002Forcid.org\u002F0000-0003-0242-7297",{"tldr":42,"method":43,"finding":44,"direction":45,"opportunity":46},"提出CBAM-LeafGAN，用选择性注意力增强StyleGAN3合成芒果叶病图像并提升识别可解释性","在StyleGAN3-t中间层选择性集成残差门控CBAM，用MangoLeafD","FID低至12.44，合成增强提升23种分类模型性能并缓解类别不平衡，Grad-CAM定位可靠。","农业人工智能与决策模型","可探索注意力引导生成模型在更多作物病害及跨域田间场景下的泛化与轻量化部署。","openalex","2026-09-15T23:30:01.657805Z"]