Parameter-Efficient Fine-Tuning of Vision Foundation Model for Forest Floor Segmentation from UAV Imagery

TL;DR

This paper adapts the Segment Anything Model for forest floor segmentation from UAV imagery using parameter-efficient fine-tuning, enabling accurate and resource-efficient segmentation of forest floor objects.

Contribution

It introduces a PEFT approach to adapt SAM for forest floor segmentation, maintaining high accuracy with fewer trainable parameters.

Findings

PEFT achieves highest mIoU in segmentation tasks.

LoRA provides a lightweight alternative for resource-limited UAVs.

Automatic segmentation without manual prompts is effective.

Abstract

Unmanned Aerial Vehicles (UAVs) are increasingly used for reforestation and forest monitoring, including seed dispersal in hard-to-reach terrains. However, a detailed understanding of the forest floor remains a challenge due to high natural variability, quickly changing environmental parameters, and ambiguous annotations due to unclear definitions. To address this issue, we adapt the Segment Anything Model (SAM), a vision foundation model with strong generalization capabilities, to segment forest floor objects such as tree stumps, vegetation, and woody debris. To this end, we employ parameter-efficient fine-tuning (PEFT) to fine-tune a small subset of additional model parameters while keeping the original weights fixed. We adjust SAM's mask decoder to generate masks corresponding to our dataset categories, allowing for automatic segmentation without manual prompting. Our results show that the adapter-based PEFT method achieves the highest mean intersection over union (mIoU), while Low-rank Adaptation (LoRA), with fewer parameters, offers a lightweight alternative for resource-constrained UAV platforms.