GROW: One-Time Training for All Grains: Open-Set Grain Recognition and Quantitative Analysis
提出无需重训练的开放集谷物识别框架，显著降低品种注册时间，对农业信息化有实质贡献。
Qihe Su、Mengyu Sun、Yuxi Ke、Zhuoyan Jiang、Wanneng Yang、Chenglong Huang、Ziyuan Yang于arXiv(2026-08-10)发表预印本。GROW是面向开放集谷物识别与定量分析的统一框架,无需重新训练即可识别新品种并完成定量分析。方法上,GROW首先进行类无关谷物定位,将混合谷物图像转换为独立实例用于品种计数和表型测量,然后将视觉嵌入与形态描述符融合为谷物描述符存储在可扩展的GrainBank中,查询谷物通过秩相似度加权top-k检索识别,新品种通过追加描述符纳入而无需更新部署模型。在渐进式品种扩展、不同谷物密度、背景域偏移场景下展现良好的可扩展性、鲁棒性和适应性,与联合重训练相比,GROW将平均类别注册时间从4153秒降至仅39秒,同时保持有竞争力的识别性能。
Abstract: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.
Comments:15 pages, 15 figures
Subjects:Computer Vision and Pattern Recognition (cs.CV)
Cite as:arXiv:2608.09345 [cs.CV]
(or arXiv:2608.09345v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.09345
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Qihe Su [view email]
[v1] Mon, 10 Aug 2026 09:21:51 UTC (42,162 KB)