ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer

TL;DR

ClusVPR introduces a clustering-based weighted transformer with an optimized VLAD layer and a pyramid self-supervised strategy, significantly improving visual place recognition accuracy and efficiency in complex scenes.

Contribution

The paper proposes a novel Clustering-based Weighted Transformer Network (CWTNet) and an optimized VLAD layer, enhancing VPR performance while reducing model complexity.

Findings

Outperforms existing models on four VPR datasets.

Achieves higher accuracy with fewer parameters.

Effectively handles duplicate regions and small objects.

Abstract

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.