Divide&Classify：面向城市级视觉地点识别的细粒度分类
Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognition
AI总结：
针对城市级密集视觉地点识别中检索推理慢的问题，提出Divide&Classify分类框架，通过空间划分与原型分类器集成实现快速高精度定位，并可加速检索流程20倍以上且提升召回率。
摘要：
视觉地点识别通常被作为图像检索问题来处理。然而，检索方法难以扩展到从城市级地图中密集采样的大规模数据集，因为其数据维度会对推理时间产生不利影响。使用近似最近邻搜索进行检索有助于缓解这一问题，但代价是性能下降。本文研究是否能够有效地将该任务作为分类问题来处理，从而绕过相似度搜索的需求。我们发现，现有的用于粗略、全球范围定位的分类方法并不适合细粒度、城市级的场景。这主要源于数据集被划分为类别的方式，因为这些方法是为处理照片的稀疏分布而设计的，因此没有考虑密集场景中自然出现的相邻类别之间的视觉混叠问题。为此，我们提出了一种划分方案，可实现快速且准确的推理，同时保持简单的学习流程；还提出了一种基于新型分类器集成的新颖推理流程，该集成使用通过角度间隔损失学习到的原型。我们的方法 Divide&Classify（D&C）兼具分类方案的快速推理能力，以及在细粒度、城市级场景中与检索方法相竞争的准确率。此外，我们表明 D&C 可以与现有检索流程结合，将计算速度提高20倍以上，同时提升其召回率，从而取得新的最先进结果。
英文摘要：
Visual Place recognition is commonly addressed as an image retrieval problem. However, retrieval methods are impractical to scale to large datasets, densely sampled from city-wide maps, since their dimension impact negatively on the inference time. Using approximate nearest neighbour search for retrieval helps to mitigate this issue, at the cost of a performance drop. In this paper we investigate whether we can effectively approach this task as a classification problem, thus bypassing the need for a similarity search. We find that existing classification methods for coarse, planet-wide localization are not suitable for the fine-grained and city-wide setting. This is largely due to how the dataset is split into classes, because these methods are designed to handle a sparse distribution of photos and as such do not consider the visual aliasing problem across neighbouring classes that naturally arises in dense scenarios. Thus, we propose a partitioning scheme that enables a fast and accurate inference, preserving a simple learning procedure, and a novel inference pipeline based on an ensemble of novel classifiers that uses the prototypes learned via an angular margin loss. Our method, Divide&Classify (D&C), enjoys the fast inference of classification solutions and an accuracy competitive with retrieval methods on the fine-grained, city-wide setting. Moreover, we show that D&C can be paired with existing retrieval pipelines to speed up computations by over 20 times while increasing their recall, leading to new state-of-the-art results.
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。
