Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network

TL;DR

This paper introduces MADAN, a novel multi-level attention domain adaptation network that significantly improves cross-regional oil palm tree detection accuracy in satellite images by addressing regional variability and limited labeling.

Contribution

The paper proposes a new domain adaptive detection method with a multi-level attention mechanism and entropy regularization, enhancing transferability across diverse regions.

Findings

MADAN improves detection accuracy by 14.98% in F1-score over baseline.

It outperforms existing domain adaptation methods by 3.55%-14.49%.

The approach effectively handles large-scale, regionally diverse satellite imagery.

Abstract

Providing an accurate evaluation of palm tree plantation in a large region can bring meaningful impacts in both economic and ecological aspects. However, the enormous spatial scale and the variety of geological features across regions has made it a grand challenge with limited solutions based on manual human monitoring efforts. Although deep learning based algorithms have demonstrated potential in forming an automated approach in recent years, the labelling efforts needed for covering different features in different regions largely constrain its effectiveness in large-scale problems. In this paper, we propose a novel domain adaptive oil palm tree detection method, i.e., a Multi-level Attention Domain Adaptation Network (MADAN) to reap cross-regional oil palm tree counting and detection. MADAN consists of 4 procedures: First, we adopted a batch-instance normalization network (BIN) based feature extractor for improving the generalization ability of the model, integrating batch normalization and instance normalization. Second, we embedded a multi-level attention mechanism (MLA) into our architecture for enhancing the transferability, including a feature level attention and an entropy level attention. Then we designed a minimum entropy regularization (MER) to increase the confidence of the classifier predictions through assigning the entropy level attention value to the entropy penalty. Finally, we employed a sliding window-based prediction and an IOU based post-processing approach to attain the final detection results. We conducted comprehensive ablation experiments using three different satellite images of large-scale oil palm plantation area with six transfer tasks. MADAN improves the detection accuracy by 14.98% in terms of average F1-score compared with the Baseline method (without DA), and performs 3.55%-14.49% better than existing domain adaptation methods.