VLAD-BuFF：面向视觉位置识别的突发感知快速特征聚合
VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition
AI总结：
本文提出VLAD-BuFF，通过自相似性特征折扣机制和PCA初始化的可学习预投影，在端到端VPR训练中解决突发性问题并加速特征聚合，在9个数据集上取得最优性能且降维12倍后仍保持高召回率。
摘要：
视觉位置识别（VPR）是许多具身智能体视觉定位流程中的关键组成部分。VPR通常被形式化为图像检索任务，旨在联合学习局部特征和聚合方法。当前最先进的VPR方法依赖VLAD聚合，该聚合可以通过特征对聚类中心的软分配来学习特征的加权贡献。然而，这一过程存在两个关键局限。首先，特征到聚类的加权没有考虑聚类内过度重复出现的结构，例如阴影或窗格；这种现象也被称为“突发性”问题，经典解决方法是在聚合之前对重复特征进行折扣处理。其次，对于具有高维局部特征的最先进图像编码器而言，特征与聚类的比较计算量很大。本文通过引入VLAD-BuFF来解决这些局限，并提出了两项新贡献：i）一种基于自相似性的特征折扣机制，用于在端到端VPR训练中学习突发感知特征；ii）通过PCA初始化的可学习预投影来降低局部特征维度，从而实现快速特征聚合。我们在9个公开数据集上对所提方法进行了基准测试，VLAD-BuFF在其中取得了新的最优性能。即使在局部特征维度降低12倍的情况下，我们的方法仍能保持较高的召回率，从而在不牺牲召回率的前提下实现快速特征聚合。通过额外的定性研究，我们展示了所提出的加权方法如何有效降低非判别性特征的权重。源代码：https://github.com/Ahmedest61/VLAD-BuFF/。
英文摘要：
Visual Place Recognition (VPR) is a crucial component of many visual localization pipelines for embodied agents. VPR is often formulated as an image retrieval task aimed at jointly learning local features and an aggregation method. The current state-of-the-art VPR methods rely on VLAD aggregation, which can be trained to learn a weighted contribution of features through their soft assignment to cluster centers. However, this process has two key limitations. Firstly, the feature-to-cluster weighting does not account for over-represented repetitive structures within a cluster, e.g., shadows or window panes; this phenomenon is also referred to as the `burstiness' problem, classically solved by discounting repetitive features before aggregation. Secondly, feature to cluster comparisons are compute-intensive for state-of-the-art image encoders with high-dimensional local features. This paper addresses these limitations by introducing VLAD-BuFF with two novel contributions: i) a self-similarity based feature discounting mechanism to learn Burst-aware features within end-to-end VPR training, and ii) Fast Feature aggregation by reducing local feature dimensions specifically through PCA-initialized learnable pre-projection. We benchmark our method on 9 public datasets, where VLAD-BuFF sets a new state of the art. Our method is able to maintain its high recall even for 12x reduced local feature dimensions, thus enabling fast feature aggregation without compromising on recall. Through additional qualitative studies, we show how our proposed weighting method effectively downweights the non-distinctive features. Source code: https://github.com/Ahmedest61/VLAD-BuFF/.
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。
