5 papers
Adaptive Kernel Density Estimation with Pre-training
Ruitong Zhang, Ke Deng
Density estimation in high-dimensional settings is an important and challenging statistical problem.Traditional methods based on kernel smoothing are inefficient in high dimensions…
Intensity-free Integral-based Learning of Marked Temporal Point Processes
Sishun Liu, Ke Deng, Xiuzhen Zhang +1
In the marked temporal point processes (MTPP), a core problem is to parameterize the conditional joint PDF (probability distribution function) for inter-event time a…
ExAgt: Expert-guided Augmentation for Representation Learning of Traffic Scenarios
Lakshman Balasubramanian, Jonas Wurst, Robin Egolf +3
Representation learning in recent years has been addressed with self-supervised learning methods. The input data is augmented into two distorted views and an encoder learns the rep…
Traffic Scenario Clustering by Iterative Optimisation of Self-Supervised Networks Using a Random Forest Activation Pattern Similarity
Lakshman Balasubramanian, Jonas Wurst, Michael Botsch +1
Traffic scenario categorisation is an essential component of automated driving, for e.\,g., in motion planning algorithms and their validation. Finding new relevant scenarios witho…
Open-set Recognition based on the Combination of Deep Learning and Ensemble Method for Detecting Unknown Traffic Scenarios
Lakshman Balasubramanian, Friedrich Kruber, Michael Botsch +1
An understanding and classification of driving scenarios are important for testing and development of autonomous driving functionalities. Machine learning models are useful for sce…