通过跨尺度一致性预训练，实现少样本植物点云分割的高效迁移。
PlantC2USeg: Cross-Scale Consistent Pre-Training for Few-Shot Unified Plant Point Cloud Segmentation
- 设计跨尺度特征对齐与受限解码机制，提升模型泛化能力。
- 仅用10个标注样本，即达83.23%实例覆盖率，优于现有方法。
- 适用于不同作物和传感器条件，适合农业三维表型研究者使用。
现代作物育种需要精确的器官级分析以实现性状量化，使植物点云分割（PPCS）日益重要。然而，传统深度学习方法严重依赖密集标注数据集，获取成本高。在分布偏移情况下，从少量样本中统一适应仍具挑战。为此，我们提出PlantC2USeg，一种基于跨尺度一致性学习的深度迁移学习框架，显式对齐多尺度特征，并采用信息受限解码策略，避免重建捷径，促进鲁棒适应。该预训练使模型在物种与传感条件变化下均能稳定实现少样本泛化，且统一微调结合继承阈值进一步降低适应开销。在Soybean3D全监督下，语义IoU与实例mWCov分别达91.91%和94.62%；仅用20个标注样本时，两项指标分别为89.78%和90.27%；10样本下仍保持83.23% mWCov和83.19% IoU。在HR3D上，10样本迁移至烟草、番茄和高粱，平均IoU为78.41%，mWCov为79.42%；22样本迁移至SYAU-Maize，IoU和mRec分别达92.75%和93.51%。此外，在ShapeNet Part上达到85.0%类别平均mIoU，证明其处理多样化形状变化的能力超越农业领域。结果表明，PlantC2USeg在分布偏移下显著降低整体适配成本，推动可扩展的植物表型分析与可迁移的3D表示学习。
原文摘要 · Abstract (English)
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.
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。