PlantC2USeg：用于小样本统一植物点云分割的跨尺度一致性预训练
PlantC2USeg: Cross-Scale Consistent Pre-Training for Few-Shot Unified Plant Point Cloud Segmentation
浏览论文内容
中文总结 AI 辅助
PlantC2USeg是含跨尺度一致性学习与信息受限解码的深度迁移学习框架，可实现植物点云的小样本统一分割，在多数据集上的全监督、小样本迁移任务中均取得领先性能，支持农业外3D表示学习。
中文摘要 AI 辅助
现代作物育种需要对性状量化进行精确的器官水平分析，这使得植物点云分割（PPCS）愈发重要。然而，传统深度学习方法严重依赖密集标注的数据集，这类数据获取成本极高。从分布偏移的样本中实现统一PPCS适配且仅需极少额外训练仍是一项挑战。为解决该问题，我们提出PlantC2USeg，这是一种深度迁移学习框架，包含跨尺度一致性学习模块，用于显式对齐不同空间尺度的特征；以及信息受限解码策略，用于避免重建捷径并提升鲁棒适配性。该预训练模型可实现跨物种和传感条件的稳定小样本泛化，而采用继承阈值的统一微调进一步降低了适配开销。在Soybean3D全监督设置下，PlantC2USeg在对比方法中取得最高的语义IoU（91.91%）和实例mWCov（94.62%）；当使用20个标注样本时，其两项指标分别达到89.78%和90.27%，领先所有对比方法；仅使用10个样本时，其仍保持最高的mWCov（83.23%），同时IoU达83.19%。在HR3D数据集上，对烟草、番茄和高粱的10次小样本迁移平均IoU为78.41%、平均mWCov为79.42%；对SYAU-Maize的22次小样本迁移则取得最高IoU（92.75%）和最高mRec（93.51%）。此外，在ShapeNet Part上取得领先的类别平均mIoU（85.0%），证明该框架具备处理农业领域之外多样形状变化的能力。这些结果表明，PlantC2USeg减少了分布偏移下的整体适配工作量，支持可扩展的植物表型分析及农业领域之外的可迁移3D表示学习。
英文摘要
Modern crop breeding demands precise organ-level analysis for trait quantification, making plant point cloud segmentation (PPCS) increasingly important. However, conventional deep learning approaches rely heavily on densely annotated datasets that are labor-intensive to acquire. Unified PPCS adaptation from distribution-shifted examples with minimal additional training remains challenging. To address this, we propose PlantC2USeg, a deep transfer learning framework featuring cross-scale consistency learning to explicitly align features across spatial scales and an information-restricted decoding strategy that prevents reconstruction shortcuts and promotes robust adaptation. The resulting pre-training enables stable few-shot generalization across species and sensing conditions, while unified fine-tuning with inherited thresholds further reduces adaptation overhead. Under full supervision on Soybean3D, PlantC2USeg achieves the highest semantic IoU and instance mWCov among compared methods, at 91.91% and 94.62%. With 20 labeled samples, it leads both metrics at 89.78% and 90.27%; with only 10 samples, it retains the highest mWCov of 83.23% while achieving 83.19% IoU. Across HR3D, 10-shot transfer to tobacco, tomato, and sorghum averages 78.41% IoU and 79.42% mWCov, while 22-shot transfer to SYAU-Maize achieves the highest IoU and mRec at 92.75% and 93.51%. Furthermore, a leading category-averaged mIoU of 85.0% on ShapeNet Part demonstrates the framework's capability to handle diverse shape variations beyond agricultural domains. These results demonstrate that PlantC2USeg reduces overall adaptation effort under distribution shifts, enabling scalable plant phenotyping and transferable 3D representation learning beyond agriculture.
发表机构
- McGill University（麦吉尔大学）
机构由 AI 辅助整理，请以论文原文为准。
