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. This has the potential to spur the application of FL to other image retrieval tasks.
Collaborative Visual Place Recognition through Federated Learning / Dutto, Mattia; Berton, Gabriele; Caldarola, Debora; Fani, Eros; Trivigno, Gabriele; Masone, Carlo. - (2024), pp. 4215-4225. (Intervento presentato al convegno IEEE / CVF Computer Vision and Pattern Recognition Conference Workshop tenutosi a Seattle (USA) nel 17-18 June 2024) [10.1109/CVPRW63382.2024.00425].
Collaborative Visual Place Recognition through Federated Learning
Dutto, Mattia;Berton, Gabriele;Caldarola, Debora;Fani, Eros;Trivigno, Gabriele;Masone, Carlo
2024
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. This has the potential to spur the application of FL to other image retrieval tasks.File | Dimensione | Formato | |
---|---|---|---|
Dutto_Collaborative_Visual_Place_Recognition_through_Federated_Learning_CVPRW_2024_paper.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
1.72 MB
Formato
Adobe PDF
|
1.72 MB | Adobe PDF | Visualizza/Apri |
Collaborative_Visual_Place_Recognition_through_Federated_Learning.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
2.24 MB
Formato
Adobe PDF
|
2.24 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2987725