Collaborative Visual Place Recognition through Federated Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 53 of its 70 references that are in the map. First posted on arXiv 20 Apr 2024.
Builds on
53 of 70 references.
References · 53
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2020Adaptive Federated Optimizationcited by 1,046
- 2016An overview of gradient descent optimization algorithmscited by 1,033
- 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
- 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
- 2018LEAF: A Benchmark for Federated Settingscited by 792
- 2021Federated Learning Based on Dynamic Regularizationcited by 562
- 2020An Efficient Framework for Clustered Federated Learningcited by 511
38 more
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
- 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
- 2021Federated Learning on Non-IID Data: A Surveycited by 346
- 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
- 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
- 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
- 2023AnyLoc: Towards Universal Visual Place Recognitioncited by 163
- 2015Particular object retrieval with integral max-pooling of CNN activationscited by 161
- 2023MixVPR: Feature Mixing for Visual Place Recognitioncited by 161
- 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 152
- 2020Federated Visual Classification with Real-World Data Distributioncited by 128
- 2023EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognitioncited by 111
- 2020Self-supervising Fine-grained Region Similarities for Large-scale Image Localizationcited by 110
- 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
- 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognitioncited by 102
- 2020VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Changecited by 101
- 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 100
- 2022Improving Generalization in Federated Learning by Seeking Flat Minimacited by 98
- 2022GSV-Cities: Toward Appropriate Supervised Visual Place Recognitioncited by 93
- 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 85
- 2018Night-to-Day Image Translation for Retrieval-based Localizationcited by 57
- 2021SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognitioncited by 57
- 2014Visual Instance Retrieval with Deep Convolutional Networkscited by 48
- 2021Hierarchical Federated Learning with Quantization: Convergence Analysis and System Designcited by 47
- 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
- 2021Cluster-driven Graph Federated Learning over Multiple Domainscited by 44
- 2021Federated Learning Meets Natural Language Processing: A Surveycited by 43
- 2023Data-efficient Large Scale Place Recognition with Graded Similarity Supervisioncited by 43
- 2022FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Drivingcited by 41
- 2020Adaptive-Attentive Geolocalization from few queries: a hybrid approachcited by 39
- 2021Viewpoint Invariant Dense Matching for Visual Geolocalizationcited by 36
- 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
- 2022Learning Sequential Descriptors for Sequence-based Visual Place Recognitioncited by 25
- 2023Swarm-SLAM : Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systemscited by 21
- 2023Are Local Features All You Need for Cross-Domain Visual Place Recognition?cited by 21
- 2021An Efficient and Scalable Collection of Fly-inspired Voting Units for Visual Place Recognition in Changing Environmentscited by 12
- 2023PlaceNav: Topological Navigation through Place Recognitioncited by 11
- 2024JIST: Joint Image and Sequence Training for Sequential Visual Place Recognitioncited by 8
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.