Toward a generic federated learning platform optimized for computer vision applications
W Zhuang - 2022 - dr.ntu.edu.sg
As a result of advances in deep learning, computer vision has transformed many industries
with a wide range of applications. The majority of these applications heavily rely on …
with a wide range of applications. The majority of these applications heavily rely on …
Scalefl: Resource-adaptive federated learning with heterogeneous clients
Federated learning (FL) is an attractive distributed learning paradigm supporting real-time
continuous learning and client privacy by default. In most FL approaches, all edge clients …
continuous learning and client privacy by default. In most FL approaches, all edge clients …
Federated learning for computer vision
Computer Vision (CV) is playing a significant role in transforming society by utilizing
machine learning (ML) tools for a wide range of tasks. However, the need for large-scale …
machine learning (ML) tools for a wide range of tasks. However, the need for large-scale …
H-FL: A hierarchical communication-efficient and privacy-protected architecture for federated learning
H Yang - arXiv preprint arXiv:2106.00275, 2021 - arxiv.org
The longstanding goals of federated learning (FL) require rigorous privacy guarantees and
low communication overhead while holding a relatively high model accuracy. However …
low communication overhead while holding a relatively high model accuracy. However …
Joint optimization in edge-cloud continuum for federated unsupervised person re-identification
Person re-identification (ReID) aims to re-identify a person from non-overlapping camera
views. Since person ReID data contains sensitive personal information, researchers have …
views. Since person ReID data contains sensitive personal information, researchers have …
Model pruning enables efficient federated learning on edge devices
Federated learning (FL) allows model training from local data collected by edge/mobile
devices while preserving data privacy, which has wide applicability to image and vision …
devices while preserving data privacy, which has wide applicability to image and vision …
Gradient Coreset for Federated Learning
D Sivasubramanian, L Nagalapatti… - Proceedings of the …, 2024 - openaccess.thecvf.com
Federated Learning (FL) is used to learn machine learning models with data that is
partitioned across multiple clients, including resource-constrained edge devices. It is …
partitioned across multiple clients, including resource-constrained edge devices. It is …
Resource-Efficient Federated Learning for Heterogenous and Resource-Constrained Environments
Federated Learning (FL) is a privacy-enforcing sub-domain of machine learning that brings
the model to the user's device for training, avoiding the need to share personal data with a …
the model to the user's device for training, avoiding the need to share personal data with a …
Local learning matters: Rethinking data heterogeneity in federated learning
Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed
learning with a network of clients (ie, edge devices). However, the data distribution among …
learning with a network of clients (ie, edge devices). However, the data distribution among …
Optimizing performance of federated person re-identification: Benchmarking and analysis
Increasingly stringent data privacy regulations limit the development of person re-
identification (ReID) because person ReID training requires centralizing an enormous …
identification (ReID) because person ReID training requires centralizing an enormous …