Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial Imagery
2026-06-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors worked on improving a computer model that detects dead trees from aerial images, which helps monitor forest health. They found that using a method called feature-level knowledge distillation allowed the model to adapt better to new forest types from different countries, even with limited new data. This method reduced mistakes and made the model's internal understanding more consistent across regions. Their results suggest this approach could help make ecological monitoring more reliable and easier to apply in varied environments.
Knowledge DistillationTreeMort-1T-UNetRemote SensingDomain AdaptationFeature-Level AlignmentMean Tree IoUInstance F1-Scoret-SNEForest Health MonitoringTransfer Learning
Authors
Anis Ur Rahman, Mete Ahishali, Einari Heinaro, Samuli Junttila
Abstract
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.