用知识蒸馏让森林死亡树检测模型跨域通用，尤其在数据少时表现更稳。
Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial Imagery
- 用特征级知识蒸馏迁移芬兰模型到波兰、德国等地的森林影像。
- 在波兰数据上达0.63的实例F1分数，误检少且对不同森林类型适应性强。
- 适合需要高精度的林业监测与生态管理场景，尤其标注数据稀缺时。
在航空影像中检测死亡树木对评估森林健康至关重要，尤其在全球气候变化导致树木死亡率上升的背景下。然而，领域差异和标注数据稀少常限制模型泛化能力。本研究改进了在芬兰影像上训练的TreeMort-1T-UNet模型，通过知识蒸馏（KD）将其适配至波兰、德国和爱沙尼亚等多样森林类型的多个目标域。对比四种KD变体（基础、自蒸馏、特征级、集成）与微调基线，采用平均树交并比（Mean Tree IoU）、实例F1分数、实例精确率和平均中心点误差等指标，并结合余弦相似度、CKA、SSIM、t-SNE及线性探测分析表征不变性。特征级KD表现最优，在波兰数据集上实现0.106的均值树交并比、0.63的实例F1分数、0.55的实例精确率和3.039的平均中心点误差；在其他目标域也保持稳健表现（如芬兰0.15，波兰0.67，德国0.60，爱沙尼亚0.59）。该方法在低数据条件下假阳性更低，深层表征具有更强不变性（如更高深层CKA/SSIM，t-SNE中更好的领域混合性，线性探测AUC达0.95），适用于高精度林业应用。消融实验证实特征对齐等组件对性能平衡的关键作用。结果表明，知识蒸馏可显著提升遥感领域中的迁移学习效果，为生态监测与可持续森林管理提供可扩展、领域鲁棒的工具。
原文摘要 · Abstract (English)
Detecting dead trees in aerial imagery is vital for assessing forest health, especially as tree mortality increases globally due to climate change, but domain variability and scarce labeled data often limit model generalization. This study advances the TreeMort-1T-UNet (Tree Mortality 1-Task U-Net) model, initially trained on Finnish aerial imagery (source domain), by applying knowledge distillation (KD) to adapt it to various target domains, including Polish, German, and Estonian datasets representing diverse forest types. We assess four KD variants: Basic, Self, Feature-level, and Ensemble, against a fine-tuning baseline, using Mean Tree IoU, Instance F1-score, Instance Precision, and Mean Centroid Error as key metrics, alongside representational analyses (e.g., cosine similarity, CKA, SSIM, t-SNE, and linear probing) for domain invariance. Feature-level KD outperforms others, yielding a Mean Tree IoU of 0.106, Instance F1-score of 0.63, Instance Precision of 0.55, and Mean Centroid Error of 3.039 on the Polish dataset, with robust precision across other target domains (e.g., 0.15 on Finnish, 0.67 on Polish, 0.60 on German, 0.59 on Estonian). It excels in low-data scenarios with fewer false positives and shows superior representational invariance (e.g., higher deep-layer CKA/SSIM, better domain mixing in t-SNE, and linear probing AUC of 0.95), making it ideal for precision-critical forestry applications. Additional ablation studies confirm that key components like feature alignment enhance its performance balance across metrics. Our findings demonstrate KD's potential to enhance transfer learning in remote sensing, offering a scalable, domain-robust tool for ecological monitoring and sustainable forest management.
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。