F
Fares Fourati
Researcher at Carthage University
Publications - 6
Citations - 30
Fares Fourati is an academic researcher from Carthage University. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 1, co-authored 2 publications receiving 4 citations.
Papers
More filters
Journal ArticleDOI
Wheat Head Detection using Deep, Semi-Supervised and Ensemble Learning
TL;DR: This paper uses semi supervised learning, precisely pseudo-labeling, to boost previous supervised models of object detection and puts much effort on ensemble learning including test time augmentation, multi-scale ensemble and bootstrap aggregating to achieve higher performance.
Journal ArticleDOI
An original framework for Wheat Head Detection using Deep, Semi-supervised and Ensemble Learning within Global Wheat Head Detection (GWHD) Dataset.
TL;DR: This paper proposes an original object detection methodology applied to Global Wheat Head Detection (GWHD) Dataset and uses semi supervised learning to boost previous supervised models of object detection and puts much effort on ensemble to achieve higher performance.
Journal Article
Bridging the Urban-Rural Connectivity Gap through Intelligent Space, Air, and Ground Networks
TL;DR: An overview of artificial intelligence (AI) techniques for improving space, air, and ground networks, hence improving connectivity in rural areas and discussing the potential positive impacts of providing connectivity to rural communities.
Proceedings ArticleDOI
Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback
TL;DR: In this article , the authors investigate the problem of unconstrained combinatorial multi-armed bandits with full-bandit feedback and stochastic rewards for submodular maximization.
Journal ArticleDOI
FilFL: Accelerating Federated Learning via Client Filtering
TL;DR: In this paper , the authors introduce a new approach to optimize client selection and training in federated learning, which is called client filtering in FLE. And they provide a thorough analysis of its convergence in a heterogeneous setting, including improved learning ability, accelerated convergence and higher test accuracy.