发表机构
Amap, Alibaba Group（高德，阿里巴巴集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对POI定位的非对称细粒度开放集问题推出首个基准GeoStore，提出GLAM方法，在多项指标上优于基线，且重排序效率更高，基准与代码将公开。
AI 中文摘要
兴趣点（POI）定位是指将用户的特写店面照片与大规模带地理标签的街景图像进行匹配，是地图构建、POI验证和基于位置的服务的基础。其最接近的现有范式是视觉地点识别（VPR），该范式假设对同一场景进行对称的全图像匹配，且尺度相当；而POI定位则需要将目标充满画面的特写查询图像，与相同POI仅占据视觉相似商铺中一个小的、偏离中心区域的宽范围参考图像进行匹配，且存在显著的拍摄域差距。我们推出了GeoStore，据我们所知，这是首个针对这种非对称、细粒度、开放集形式的基准，并表明为对称VPR调优的全局描述符方法在该基准上存在系统性局限，因为单个全局向量会稀释小型目标。我们进一步提出了GLAM（全局到局部非对称匹配），它将检索锚定的全局描述符与非对称局部路径耦合：每个参考图像被保留为一组池化区域标记的紧凑集合，并通过可学习的软后期交互与单个查询探针匹配；在推理时，相同的标记支持轻量级的互最近邻重排序。GLAM在Recall@1/5/10和mAP上优于强大的全局和两阶段基线，其重排序特征小约5倍，每对匹配成本比现有局部重排序低约两个数量级。该基准和代码将公开发布。
英文摘要
Point-of-interest (POI) localization matches user-provided storefront close-ups to the same shops in wide, geo-tagged vehicle-mounted street views. POIs may change while the surrounding scene stays similar, so scene-level recognition alone cannot establish POI identity. Differences in target scale and capture domains further challenge matching. We introduce POI-Loc, to our knowledge the first benchmark dedicated to this asymmetric, fine-grained POI localization task. Many visual place recognition methods represent each image with a single global vector, which tends to dilute fine-grained features of small storefronts amid background clutter. We propose GLAM (Global-to-Local Asymmetric Matching) to combine global and local evidence. In stage one, a single attention-pooled query probe is matched against compact reference region tokens via learnable soft top-k interaction, with the resulting local similarity fused with global similarity for retrieval. Stage two reuses query region tokens before attention pooling and stored reference tokens for mutual-nearest-neighbor re-ranking. GLAM surpasses both global and two-stage baselines on Recall@1/5/10 and mAP, with about $5\times$ smaller re-ranking features and $280\times$ lower per-pair matching cost than FoL. The benchmark and code will be released at https://github.com/roadhan/glam.
Comments5 pages, 3 figures. Submitted to ICASSP 2027
