FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
arXiv:2111.11066
Abstract
Federated Learning (FL) is a distributed learning paradigm that can learn a global or personalized model from decentralized datasets on edge devices. However, in the computer vision domain, model performance in FL is far behind centralized training due to the lack of exploration in diverse tasks with a unified FL framework. FL has rarely been demonstrated effectively in advanced computer vision tasks such as object detection and image segmentation. To bridge the gap and facilitate the development of FL for computer vision tasks, in this work, we propose a federated learning library and benchmarking framework, named FedCV, to evaluate FL on the three most representative computer vision tasks: image classification, image segmentation, and object detection. We provide non-I.I.D. benchmarking datasets, models, and various reference FL algorithms. Our benchmark study suggests that there are multiple challenges that deserve future exploration: centralized training tricks may not be directly applied to FL; the non-I.I.D. dataset actually downgrades the model accuracy to some degree in different tasks; improving the system efficiency of federated training is challenging given the huge number of parameters and the per-client memory cost. We believe that such a library and benchmark, along with comparable evaluation settings, is necessary to make meaningful progress in FL on computer vision tasks. FedCV is publicly available: https://github.com/FedML-AI/FedCV.
arXiv commentFederated Learning for Computer Vision, an application of FedML Ecosystem (fedml.ai)
References in corpus (34)
- YOLOv4: Optimal Speed and Accuracy of Object Detection
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- On the Convergence of FedAvg on Non-IID Data
- How To Backdoor Federated Learning
- SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
- AutoAugment: Learning Augmentation Policies from Data
- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
- Differentially Private Federated Learning: A Client Level Perspective
- Exploring Simple Siamese Representation Learning
- Can You Really Backdoor Federated Learning?
- Personalized Federated Learning: A Meta-Learning Approach
- Mitigating Sybils in Federated Learning Poisoning
- FedML: A Research Library and Benchmark for Federated Machine Learning
- A generic framework for privacy preserving deep learning
- Three Approaches for Personalization with Applications to Federated Learning
- HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning
- Agnostic Federated Learning
- Practical Secure Aggregation for Federated Learning on User-Held Data
- Split learning for health: Distributed deep learning without sharing raw patient data
- A Field Guide to Federated Optimization
- Adaptive Federated Optimization
- FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
- A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
- Salvaging Federated Learning by Local Adaptation
- Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization
- Central Server Free Federated Learning over Single-sided Trust Social Networks
- Federated Learning with Only Positive Labels
- Personalized Cross-Silo Federated Learning on Non-IID Data
- Federated Reconstruction: Partially Local Federated Learning
- Backdoor Attacks on Federated Meta-Learning
- SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision
- Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data
- Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
- Fed-Sim: Federated Simulation for Medical Imaging