发表机构
National Key Laboratory of Crop Genetic Improvement; National Center of Plant Gene Research; Hubei Hongshan Laboratory; Huazhong Agricultural University; College of Engineering, Huazhong Agricultural University; Engineering Research Center of Intelligent Technology for Agriculture, Ministry of Education; School of Cyber Science and Engineering, Sichuan University（作物遗传改良国家重点实验室; 国家植物基因研究中心; 湖北洪山实验室; 华中农业大学; 华中农业大学工程学院; 教育部农业智能技术工程研究中心; 四川大学网络空间安全学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出无需重新训练的开放集谷物识别框架GROW，可高效纳入新品种，缩短品种注册时间，同时保持识别性能，为谷物识别与定量分析提供可扩展方案。
AI 中文摘要
作物育种的进展催生了越来越多的谷物品种，对高效的品种识别与定量分析的需求日益增长。然而，现有方法通常在固定的品种集上进行训练，若要纳入新引入的品种则需要额外的数据收集与模型重新训练。为解决这一局限，我们提出了GROW（无需重新训练的开放集谷物识别与定量分析框架）。GROW首先执行与类别无关的谷物定位，将混合谷物图像转换为单个实例，以便进行品种计数和表型测量；随后将视觉嵌入与形态学描述符结合，存储到可扩展的GrainBank中，形成融合谷物描述符。查询谷物通过秩相似度加权的top-k检索进行识别，新引入的品种可通过追加其描述符纳入，无需更新已部署的模型。在品种逐步扩展、谷物密度变化以及背景域偏移的多种实验设置下，我们验证了GROW的可扩展性、鲁棒性与适应性。与联合重新训练相比，GROW将平均品种注册时间从4153秒缩短至仅39秒，同时保持了具有竞争力的识别性能。这些结果表明，GROW为可扩展的谷物识别、计数及表型分析提供了一种高效且可维护的解决方案，无需反复进行模型重新训练。
英文摘要
Advances in crop breeding have introduced an increasing number of grain varieties, creating a growing demand for efficient variety recognition and quantitative analysis. However, existing methods are typically trained on a fixed variety set, and incorporating newly introduced varieties requires additional data collection and model retraining. To address this limitation, we propose GROW, a framework for Grain Recognition and quantitative analysis in Open sets Without retraining. GROW first performs class-agnostic grain localization, converting mixed-grain images into individual instances for variety-wise counting and phenotypic measurement. It then combines visual embeddings and morphological descriptors into fused grain descriptors stored in an extensible GrainBank. Query grains are recognized through rank-similarity weighted top-k retrieval, and newly introduced varieties are incorporated by appending their descriptors without updating the deployed models. Extensive experiments under progressive variety expansion, varying grain densities, and background domain shifts demonstrate the scalability, robustness, and adaptability of GROW. Compared with joint retraining, GROW reduced the average category-registration time from 4153 s to only 39 s while maintaining competitive recognition performance. These results demonstrate that GROW provides an efficient and maintainable solution for extensible grain recognition, counting, and phenotypic analysis without repeated model retraining.
Comments15 pages, 15 figures
