Resource-Efficient Adaptation of the Segment Anything Model for Urban Land-Cover Mapping
Resource-Efficient Adaptation of the Segment Anything Model for Urban Land-Cover Mapping
Mohammad Baradaran Aghghaleh1 Khorshid Mehrabi2 Helya Haji3 Ali Yazdani4
1) SR.C., Islamic Azad University, Tehran, Iran, Email:
2) SR.C., Islamic Azad University, Tehran, Iran, Email:
3) SR.C., Islamic Azad University, Tehran, Iran, Email:
4) SR.C., Islamic Azad University, Tehran, Iran, Email:
IOI Code
:
AAHD-ABKHKD
Publication :
National Conference on Information Technology, Nanotechnology, Artificial Intelligence and Technological Futures Studies(itnaf.ir)
Abstract :
High-resolution land-cover mapping from remote sensing imagery is essential for urban monitoring, environmental assessment, and sustainable planning. However, adapting foundation models for semantic segmentation typically requires substantial computational resources, limiting their practical adoption. This study presents a parameter-efficient adaptation framework based on the Segment Anything Model (SAM) that enables effective semantic segmentation of remote sensing imagery on resource-constrained hardware. The proposed framework combines selective fine-tuning with Low-Rank Adaptation (LoRA) and an imbalance-aware training strategy, reducing the number of trainable parameters to 33 million (65% fewer than full fine-tuning) while maintaining competitive performance. Experiments on the OpenEarthMap benchmark dataset achieve 51.59% mIoU with Test-Time Augmentation, outperforming baseline models under identical training conditions and exceeding the performance reported by other SAM-based approaches on the same benchmark dataset. Resolution ablation experiments further indicate that an input size of 512×512 provides a balance between segmentation performance and computational cost, making the proposed framework suitable for deployment on limited hardware resources. Beyond semantic segmentation, the resulting land-cover maps enable estimation of Green Space Ratio and Impervious Surface Ratio. These results demonstrate that foundation models can be efficiently adapted for practical remote sensing applications under limited computational resources while supporting reliable urban-scale environmental analysis.
Keywords : segment anything model sam openearthmap lora remote sensing