Collaborative Visual Place Recognition through Federated Learning

TL;DR

This paper introduces FedVPR, a federated learning framework for visual place recognition that addresses data heterogeneity and the lack of class labels, enabling decentralized training of image retrieval models.

Contribution

It proposes a novel federated learning approach for VPR, tackling challenges like data heterogeneity and contrastive learning without centralized data collection.

Findings

Demonstrates effective federated training of VPR models.

Addresses data heterogeneity and lack of labels in FL setting.

Establishes a new challenging task for FL research.

Abstract

Visual Place Recognition (VPR) aims to estimate the location of an image by treating it as a retrieval problem. VPR uses a database of geo-tagged images and leverages deep neural networks to extract a global representation, called descriptor, from each image. While the training data for VPR models often originates from diverse, geographically scattered sources (geo-tagged images), the training process itself is typically assumed to be centralized. This research revisits the task of VPR through the lens of Federated Learning (FL), addressing several key challenges associated with this adaptation. VPR data inherently lacks well-defined classes, and models are typically trained using contrastive learning, which necessitates a data mining step on a centralized database. Additionally, client devices in federated systems can be highly heterogeneous in terms of their processing capabilities. The proposed FedVPR framework not only presents a novel approach for VPR but also introduces a new, challenging, and realistic task for FL research, paving the way to other image retrieval tasks in FL.