发表机构
University of Southampton（南安普顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对越野导航罕见故障导致的危险识别难题，提出参数高效的GAFT方法，通过几何先验指导LoRA适配，在森林危险基准上显著提升了留一场景重复平均F₂
AI 中文摘要
越野导航可能因物理结构引发无法恢复的状态（如高位卡滞或被困）而失败，需要人工干预。识别这些结构至关重要但极具挑战性，因为此类故障事件罕见且收集成本高昂，导致训练数据有限。此外，收集的数据仅关联图像帧与结果，未指明导致故障的视觉线索，直接学习这些数据会利用特定场景的视觉线索，导致泛化性差。我们提出**地理锚定微调（Geo-Anchored Fine-Tuning，GAFT）**，这是一种参数高效的方法，通过几何衍生先验适配视觉基础模型，它通过将空间注意力回滚图与几何先验对齐来指导LoRA适配，同时保留预训练表示。在经干预验证的森林危险基准上，经过10次独立训练的适配，GAFT始终优于冻结的DINOv2和有监督PEFT基线，配对分析下的留一场景重复平均F₂从0.0607提升至0.3757，具有统计显著性；其中表现最佳的GAFT模型的留一重复F₂达0.570。代码和基准：此httpsURL
英文摘要
Off-road navigation can fail when physical structures induce irrecoverable states such as high-centering or entrapment, requiring human interventions. Identifying these structures is crucial, yet challenging. Such failure events are rare and costly to collect, resulting in limited training data. Moreover, the collected data associate frames with outcomes, but do not indicate the visual cues responsible for the failure. Learning directly from these data can therefore exploit scenario-specific visual cues, leading to poor generalization. We propose \textbf{Geo-Anchored Fine-Tuning (GAFT)}, a parameter-efficient method that adapts a vision foundation model with a geometry-derived prior. It guides LoRA adaptation by aligning a spatial attention-rollout map with the geometry prior, while preserving pretrained representations. On an intervention-verified forest hazard benchmark, across ten independently trained adaptations, GAFT consistently outperforms frozen DINOv2 and supervised PEFT baselines, improving the repeated leave-one-scenario-out mean $F_2$ from 0.0607 to 0.3757 with statistical significance under paired analysis. Within these independently trained models, the best-performing GAFT model achieves a repeated-LOSO $F_2$ of 0.570. Code and benchmark: https://github.com/Xu-Yanran/geo_anchored_fine_tuning
