Precision-recall divergence optimization for generative modeling with GANs and normalizing flows

A Verine, B Negrevergne, MS Pydi… - Advances in Neural …, 2023 - proceedings.neurips.cc
Achieving a balance between image quality (precision) and diversity (recall) is a significant
challenge in the domain of generative models. Current state-of-the-art models primarily rely …

Go with the flows: Mixtures of normalizing flows for point cloud generation and reconstruction

J Postels, M Liu, R Spezialetti… - … Conference on 3D …, 2021 - ieeexplore.ieee.org
Recently Normalizing Flows (NFs) have demonstrated state-of-the-art performance on
modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time …

Bayesian inversion, uncertainty analysis and interrogation using boosting variational inference

X Zhao, A Curtis - Journal of Geophysical Research: Solid …, 2024 - Wiley Online Library
Geoscientists use observed data to estimate properties of the Earth's interior. This often
requires non‐linear inverse problems to be solved and uncertainties to be estimated …

Synthetic Sensor Data Generation Exploiting Deep Learning Techniques and Multi-Modal Information

F Romanelli, F Martinelli - IEEE Sensors Letters, 2023 - ieeexplore.ieee.org
In recent years, deep learning techniques have revolutionized the field of data generation,
including the creation of synthetic sensor data. The ability to generate large quantities of …

On the Quantification of Image Reconstruction Uncertainty without Training Data

J Zhang, S Bi, V Fung - … of the IEEE/CVF Winter Conference …, 2024 - openaccess.thecvf.com
Computational imaging plays a pivotal role in determining hidden information from sparse
measurements. A robust inverse solver is crucial to fully characterize the uncertainty induced …

Distributional gradient boosting machines

A März, T Kneib - arxiv preprint arxiv:2204.00778, 2022 - arxiv.org
We present a unified probabilistic gradient boosting framework for regression tasks that
models and predicts the entire conditional distribution of a univariate response variable as a …

Synthetic sensor measurement generation with noise learning and multi-modal information

F Romanelli, F Martinelli - IEEE Access, 2023 - ieeexplore.ieee.org
Deep learning has transformed data generation, particularly in creating synthetic sensor
data. This capability is invaluable in fields like autonomous driving, robotics, and computer …

On the Quantification of Image Reconstruction Uncertainty without Training Data

S Bi, V Fung, J Zhang - arxiv preprint arxiv:2311.09639, 2023 - arxiv.org
Computational imaging plays a pivotal role in determining hidden information from sparse
measurements. A robust inverse solver is crucial to fully characterize the uncertainty induced …

Training Algorithms for Mixtures of Normalizing Flows Check for updates

S Ciobanu - … Science and Network Engineering: Proceedings of …, 2023 - books.google.com
In this paper, we focus on how a probabilistic mixture of normalizing flows can be fitted. In
the literature, there are (at least) four approaches that do not necessarily provide an actual …

Training Algorithms for Mixtures of Normalizing Flows

S Ciobanu - International Conference on Data Science and Network …, 2023 - Springer
In this paper, we focus on how a probabilistic mixture of normalizing flows can be fitted. In
the literature, there are (at least) four approaches that do not necessarily provide an actual …