Confidence-Based Federated Distillation for Vision-Based Lane-Centering
Authors:
- 4 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
A fundamental challenge of autonomous driving is maintaining the vehicle in the center of the lane by adjusting the steering angle. Recent advances leverage deep neural networks to predict steering decisions directly from images captured by the car cameras. Machine learning-based steering angle prediction needs to consider the vehicle’s limitation in uploading large amounts of potentially private data for model training. Federated learning can address these constraints by enabling multiple vehicles to collaboratively train a global model without sharing their private data, but it is difficult to achieve good accuracy as the data distribution is often non-i.i.d. across the vehicles. This paper presents a new confidence-based federated distillation method to improve the performance of federated learning for steering angle prediction. Specifically, it proposes the novel use of entropy to determine the predictive confidence of each local model, and then selects the most confident local model as the teacher to guide the learning of the global model. A comprehensive evaluation of vision-based lane centering shows that the proposed approach can outperform FedAvg and FedDF by 11.3% and 9%, respectively.Keywords
All Related Versions
Funding Information
- National Science Foundation
This publication has 12 references indexed in Scilit:
- Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning2022
- Boosting Active Learning via Improving Test PerformanceProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Federated Learning on Non-IID Data Silos: An Experimental Study2022
- FedAUX: Leveraging Unlabeled Auxiliary Data in Federated LearningIEEE Transactions on Neural Networks and Learning Systems, 2021
- A Survey of Deep Active LearningACM Computing Surveys, 2021
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning2020
- Controlling Steering Angle for Cooperative Self-driving Vehicles utilizing CNN and LSTM-based Deep Networks2019
- Cost-Effective Active Learning for Deep Image ClassificationIEEE Transactions on Circuits and Systems for Video Technology, 2016
- Deep Residual Learning for Image Recognition2016
- Heterogeneous Uncertainty Sampling for Supervised Learning1994