Cross-Domain Transfer Learning for Road Extraction from Satellite to UAV

High-resolution UAV imagery offers great potential for detailed road extraction in complex environments, but annotated UAV datasets remain scarce and costly to acquire. In contrast, satellite imagery is abundant and globally available, though its resolution is limited. Recent foundation models such as AnySat (CVPR 2025) demonstrate the effectiveness of large-scale multi-modal embeddings for Earth observation tasks, yet they do not address the cross-domain gap between satellite and UAV data, nor the challenges of few-shot or zero-shot road extraction.

This work investigates cross-domain transfer learning, leveraging satellite-based embeddings as a source of knowledge and adapting them to UAV imagery through lightweight adapters, feature alignment, and embedding-based inference, highlighting the novelty of embedding-level transfer for UAV road extraction. The goal is to achieve robust UAV road extraction with minimal or no UAV-specific annotations, clarifying the positioning of zero-shot as exploratory while few-shot is the primary target.

Tasks to be performed by the student will include:

· Review related works on transfer learning, few-shot and zero-shot methods, and domain adaptation in remote sensing.

· Study embedding alignment methods (contrastive learning, adversarial domain adaptation, statistical distribution matching).

· Create a transfer pipeline from satellite embeddings to UAV imagery with lightweight adapter networks.

· Design few-shot or zero-shot learning strategies for road-map extraction, including prototype-based inference to leverage limited UAV annotations.

· Verify performance through experiments on UAV datasets (e.g., UAVid / VisDrone), with evaluation metrics such as mIoU, F1-score, APLS, and connectivity metrics.

· Conduct ablation studies on alignment strategies, adapter designs, and embedding update schemes.

Note：Applicant will use publicly available datasets and receive technical support from SZTAKI.

Supervisor at the department: Dr. Chang Liu, Assistant Professor

External supervisor:   Prof. Tamás Szirányi, HUN-REN SZTAKI.