解决城市视觉定位中的地理数据分布不均问题，提升冷门区域识别能力。
Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition
- 提出DAPR框架，按类别分布重加权梯度，平衡长尾数据影响。
- 在SF-XL测试集上提升18.3%（v1）和6.7%（v2），显著改善冷门区域表现。
- 可插拔设计，适配多种主流视觉定位方法与数据集。
城市尺度视觉定位（VPR）旨在通过匹配查询图像与地理标记数据库来识别位置。尽管现有方法表现优异，却忽视了城市级数据集中存在的严重长尾分布问题，导致模型偏向高密度拍摄区域，忽略低频访问区域。本文系统分析该不平衡挑战，提出分布感知的视觉定位（DAPR）框架——一种模型无关的即插即用机制，通过重平衡头尾类别梯度贡献，缓解偏差。此外，在分类-检索流程中，DAPR引入多尺度距离搜索，计算每类分布紧凑性，进一步提升检索阶段性能。在大规模SF-XL基准上，相比此前分类-检索基线，DAPR在v1测试集上提升18.3%，在v2测试集上提升6.7%。作为插件模块，其在SF-XL、MSLS和Pitts30k等多个基准上对代表性VPR方法均实现一致提升，展现出广泛的通用性。
原文摘要 · Abstract (English)
Urban-scale Visual Place Recognition (VPR) aims to identify the geographic location of a query image by matching it against a geo-tagged database. While recent methods achieve impressive performance, they overlook a serious long-tailed problem hidden in urban-scale datasets, which biases the model towards locations with abundant images and ignores less-visited areas, causing models to systematically favor frequently photographed locations while failing in sparsely covered areas. In this paper, we systematically characterize this imbalance challenge and propose Distribution-Aware Place Recognition (DAPR), a model-agnostic plug-in framework that rebalances gradient contributions across head and tail classes. Additionally, within classification-retrieval pipelines, DAPR applies a multi-scale distance search mechanism to compute per-class distributional compactness, providing complementary gains at the retrieval stage. On the large-scale SF-XL benchmark, our framework outperforms the previous classification-retrieval baseline by 18.3% on test set v1, and 6.7% on test set v2. As a plug-in module, it achieves consistent improvements across representative VPR methods on SF-XL, MSLS, and Pitts30k, demonstrating broad generalizability across different methods and benchmarks.
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。