ClusVPR：基于聚类的加权Transformer的高效视觉地点识别
ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer
AI总结：
ClusVPR提出基于聚类的加权Transformer网络（CWTNet）和优化VLAD层，结合金字塔自监督策略，解决视觉地点识别中重复区域和小物体问题，在四个数据集上以更低复杂度实现更优性能。
摘要：
视觉地点识别（VPR）是一项极具挑战性的任务，具有广泛的应用，包括机器人导航和自动驾驶车辆。由于重复区域的存在以及复杂场景中对小物体缺乏关注，VPR尤其困难，导致识别偏差。在本文中，我们提出了ClusVPR，一种新颖的方法，解决了重复区域中的冗余信息和小物体表示的具体问题。与依赖卷积神经网络（CNN）生成特征图的现有方法不同，ClusVPR引入了一种称为基于聚类的加权Transformer网络（CWTNet）的独特范式。CWTNet利用基于聚类的加权特征图的力量，并整合全局依赖关系，以有效解决大规模VPR问题中遇到的视觉偏差。我们还引入了优化-VLAD（OptLAD）层，该层显著减少了参数数量并提高了模型效率。该层专门设计用于聚合从尺度级图像块中获得的信息。此外，我们的金字塔自监督策略专注于从尺度级图像块中提取代表性和多样性的信息，而不是整个图像，这对于在VPR中捕获代表性和多样性的信息至关重要。在四个VPR数据集上的大量实验表明，我们的模型在复杂度更低的情况下，性能优于现有模型。
英文摘要：
Visual place recognition (VPR) is a highly challenging task that has a wide range of applications, including robot navigation and self-driving vehicles. VPR is particularly difficult due to the presence of duplicate regions and the lack of attention to small objects in complex scenes, resulting in recognition deviations. In this paper, we present ClusVPR, a novel approach that tackles the specific issues of redundant information in duplicate regions and representations of small objects. Different from existing methods that rely on Convolutional Neural Networks (CNNs) for feature map generation, ClusVPR introduces a unique paradigm called Clustering-based Weighted Transformer Network (CWTNet). CWTNet leverages the power of clustering-based weighted feature maps and integrates global dependencies to effectively address visual deviations encountered in large-scale VPR problems. We also introduce the optimized-VLAD (OptLAD) layer that significantly reduces the number of parameters and enhances model efficiency. This layer is specifically designed to aggregate the information obtained from scale-wise image patches. Additionally, our pyramid self-supervised strategy focuses on extracting representative and diverse information from scale-wise image patches instead of entire images, which is crucial for capturing representative and diverse information in VPR. Extensive experiments on four VPR datasets show our model's superior performance compared to existing models while being less complex.
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。
