用视觉语言模型对跨视角地理定位结果进行重排序，提升精准度。
Zero-shot Vision-Language Reranking for Cross-View Geolocalization
- 采用双阶段框架：先检索再用VLM做相对排序
- 配对比较策略使顶级匹配准确率显著提升
- 适合关注定位精度、无需额外标注数据的研究者
跨视角地理定位系统虽能召回大量相关候选（高Recall@k），但难以选出最优匹配（低Top-1准确率）。本文探索使用零样本视觉语言模型（VLM）作为重排序器来弥补这一差距。提出两阶段框架：先使用当前最佳检索方法，再通过VLM进行重排序。系统比较了两种策略：点式（单独评分）与配对式（相对比较）。在VIGOR数据集上的实验显示，所有点式方法均导致性能灾难性下降或无变化；而采用LLaVA的配对策略则显著提升了Top-1准确率。分析表明，这些VLM对绝对相关性评分校准不佳，但擅长细粒度的相对视觉判断，因此配对重排序是提升CVGL精度的可行方向。
原文摘要 · Abstract (English)
Cross-view geolocalization (CVGL) systems, while effective at retrieving a list of relevant candidates (high Recall@k), often fail to identify the single best match (low Top-1 accuracy). This work investigates the use of zero-shot Vision-Language Models (VLMs) as rerankers to address this gap. We propose a two-stage framework: state-of-the-art (SOTA) retrieval followed by VLM reranking. We systematically compare two strategies: (1) Pointwise (scoring candidates individually) and (2) Pairwise (comparing candidates relatively). Experiments on the VIGOR dataset show a clear divergence: all pointwise methods cause a catastrophic drop in performance or no change at all. In contrast, a pairwise comparison strategy using LLaVA improves Top-1 accuracy over the strong retrieval baseline. Our analysis concludes that, these VLMs are poorly calibrated for absolute relevance scoring but are effective at fine-grained relative visual judgment, making pairwise reranking a promising direction for enhancing CVGL precision.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。