Search Results for author:
Found 4 papers, 1 papers with code
Defensive Perception: Estimation and Monitoring of Neural Network Performance under Deployment
To address this, we propose to encapsulate the neural network under deployment within an uncertainty estimation envelope that is based on the epistemic uncertainty estimation through the Monte Carlo Dropout approach.
Methods for the frugal labeler: Multi-class semantic segmentation on heterogeneous labels
This paper discusses the effects of frugal labeling and proposes to train neural networks for multi-class semantic segmentation on heterogeneously labeled data based on a novel objective function.
Ranked #1 on
2D Semantic Segmentation
on Extended heartSeg
Distributed traffic light control at uncoupled intersections with real-world topology by deep reinforcement learning
Different strategies, containing fixed-time, gap-based and time-based control approaches as well as our deep reinforcement learning based control approach, are implemented and assessed.
Transfer Learning versus Multi-agent Learning regarding Distributed Decision-Making in Highway Traffic
Transportation and traffic are currently undergoing a rapid increase in terms of both scale and complexity.
