接近，但尚未到位：提升视觉位置识别中的地理距离敏感性
Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition
AI总结：
针对单阶段VPR嵌入地理距离敏感性不足导致top-k排序错误的问题，提出CliqueMining图团采样挖掘策略，显著提升小距离范围识别召回率。
摘要：
视觉位置识别（Visual Place Recognition，VPR）在许多定位与建图流程中发挥着关键作用。它包括在某个嵌入空间中，从带有地理标签的参考图像数据库里检索与查询图像最接近的样本。图像嵌入经过学习，能够在视觉外观、视点和几何结构发生变化时仍有效描述一个地点。在本研究中，我们阐述了当前VPR嵌入在地理距离敏感性方面的局限如何导致top-k检索结果出现错误排序的高概率，从而对召回率产生负面影响。为解决单阶段VPR中的这一问题，我们提出了一种新颖的挖掘策略CliqueMining，该策略通过从视觉相似图像构成的图中采样团（cliques）来选择正样本和负样本。我们的方法提升了VPR嵌入在小距离范围内的敏感性，并在相关基准上显著改进了当前最先进水平。具体而言，我们在MSLS Challenge中将recall@1从75%提高到82%，在Nordland中从76%提高到90%。模型和代码可在https://github.com/serizba/cliquemining获取。
英文摘要：
Visual Place Recognition (VPR) plays a critical role in many localization and mapping pipelines. It consists of retrieving the closest sample to a query image, in a certain embedding space, from a database of geotagged references. The image embedding is learned to effectively describe a place despite variations in visual appearance, viewpoint, and geometric changes. In this work, we formulate how limitations in the Geographic Distance Sensitivity of current VPR embeddings result in a high probability of incorrectly sorting the top-k retrievals, negatively impacting the recall. In order to address this issue in single-stage VPR, we propose a novel mining strategy, CliqueMining, that selects positive and negative examples by sampling cliques from a graph of visually similar images. Our approach boosts the sensitivity of VPR embeddings at small distance ranges, significantly improving the state of the art on relevant benchmarks. In particular, we raise recall@1 from 75% to 82% in MSLS Challenge, and from 76% to 90% in Nordland. Models and code are available at https://github.com/serizba/cliquemining.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
