What question did this study set out to answer?

The aim is to enhance forest segmentation accuracy across plantation and natural forests using a refined deep learning architecture.

February 8, 2026Open Access

Enhancing Cross-Regional Generalization in UAV Forest Segmentation Across Plantation and Natural Forests with Attention-Refined PP-LiteSeg Networks

XMXinyu MaSouthwest Forestry University SZShuang ZhangSouthwest Forestry University KLKaibo LiSouthwest Forestry University

Key Points

The aim is to enhance forest segmentation accuracy across plantation and natural forests using a refined deep learning architecture.
Developed two versions of PP-LiteSeg architecture for forest segmentation.
Implemented a multi-branch attention fusion module in Version 01 for feature enhancement.
Introduced a lightweight residual connection in Version 02 for improved feature stability.
Conducted comparisons against various CNN and transformer-based segmentation models.
Evaluated performance in cross-regional transfer scenarios.
Version 01 achieved a mean Intersection over Union (mIoU) of 92.64% and an F1-score of 96.10%.
Version 02 attained an mIoU of 91.87% and an F1-score of 95.77%, showing significant improvement over other models.
Version 02 demonstrated minimal performance degradation in cross-region scenarios, indicating strong generalization ability.
On a combined dataset, Version 02 reached a leading mIoU of 91.50%, outperforming several established models.

Abstract

Accurate fine-scale forest mapping is fundamental for ecological monitoring and resource management. While deep learning semantic segmentation methods have advanced the interpretation of high-resolution UAV imagery, their generalization across diverse forest regions remains challenging due to high spatial heterogeneity. To address this, we propose two enhanced versions based on the PP-LiteSeg architecture for robust cross-regional forest segmentation. Version 01 (V01) integrates a multi-branch attention fusion module composed of parallel channel, spatial, and pixel attention branches. This design enables fine-grained feature enhancement and precise boundary delineation in structurally regular artificial forests, such as the Huayuan Forest Farm. As a result, V01 achieves a mIoU of 92.64% and an F1-score of 96.10%, representing an approximately 18 percentage-point mIoU improvement over PSPNet and DeepLabv3+. Building on this, Version 02 (V02) introduces a lightweight residual connection that directly shortcuts the fused features, thereby improving feature stability and robustness under complex textures and illumination, and demonstrates stronger performance in naturally heterogeneous forests (Longhai Township), attaining an mIoU of 91.87% and an F1-score of 95.77% (5.72 percentage-point mIoU gain over DeepLabv3+). We further conduct comprehensive comparisons against conventional CNN baselines as well as representative lightweight and transformer-based models (BiSeNetV2 and SegFormer-B0). In bidirectional cross-region transfer (train on one region and directly test on the other), V02 exhibits the most stable performance with minimal degradation, highlighting its robustness under domain shift. On a combined cross-regional dataset, V02 achieves a leading mIoU of 91.50%, outperforming U-Net, DeepLabv3+, and PSPNet. In summary, V01 excels in boundary delineation for regular plantation forests, whereas V02 shows more stable generalization across highly varied natural forest landscapes, providing practical solutions for region-adaptive UAV forest segmentation.

AIに質問

Bookmark

View Full Paper