Related papers: Continuous Normalizing Flows for Uncertainty-Aware…

Normalizing Flows (NFs) are able to model complicated distributions p(y) with strong inter-dimensional correlations and high multimodality by transforming a simple base density p(z) through an invertible neural network under the change of…

Normalizing Flows (NF) are Generative models which transform a simple prior distribution into the desired target. They however require the design of an invertible mapping whose Jacobian determinant has to be computable. Recently introduced,…

This paper presents a groundbreaking approach to causal inference by integrating continuous normalizing flows (CNFs) with parametric submodels, enhancing their geometric sensitivity and improving upon traditional Targeted Maximum Likelihood…

We present a data-driven approach for probabilistic wind power forecasting based on conditional normalizing flow (CNF). In contrast with the existing, this approach is distribution-free (as for non-parametric and quantile-based approaches)…

In recent times, there has been a growing interest in developing effective perception techniques for combining information from multiple modalities. This involves aligning features obtained from diverse sources to enable more efficient…

Continuous Normalizing Flows (CNFs) have emerged as promising deep generative models for a wide range of tasks thanks to their invertibility and exact likelihood estimation. However, conditioning CNFs on signals of interest for conditional…

Object pose estimation is a fundamental problem in computer vision and plays a critical role in virtual reality and embodied intelligence, where agents must understand and interact with objects in 3D space. Recently, score based generative…

Turbulent flows play an important role in many scientific and technological design problems. Both Sub-Grid Scale (SGS) models in Large Eddy Simulations (LES) and Reynolds Averaged Navier Stokes (RANS) based modeling will require turbulence…

Protected natural areas play a vital role in ecological balance and ecosystem services. Monitoring these regions at scale using satellite imagery and machine learning is promising, but current methods often lack interpretability and…

Although methods for estimating the pose of objects in indoor scenes have achieved great success, the pose estimation of underwater objects remains challenging due to difficulties brought by the complex underwater environment, such as…

Normalizing flow (NF) has gained popularity over traditional maximum likelihood based methods due to its strong capability to model complex data distributions. However, the standard approach, which maps the observed data to a normal…

Medical image segmentation is inherently an ambiguous task due to factors such as partial volumes and variations in anatomical definitions. While in most cases the segmentation uncertainty is around the border of structures of interest,…

We propose UniPose, a unified framework for human pose estimation, based on our "Waterfall" Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods…

The Normalizing Flow (NF) models a general probability density by estimating an invertible transformation applied on samples drawn from a known distribution. We introduce a new type of NF, called Deep Diffeomorphic Normalizing Flow (DDNF).…

Bayesian inference with computationally expensive likelihood evaluations remains a significant challenge in many scientific domains. We propose normalizing flow regression (NFR), a novel offline inference method for approximating posterior…

Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…

Counterfactual explanations (CFEs) guide users on how to adjust inputs to machine learning models to achieve desired outputs. While existing research primarily addresses static scenarios, real-world applications often involve data or model…

We introduce Random Projection Flows (RPFs), a principled framework for injective normalizing flows that leverages tools from random matrix theory and the geometry of random projections. RPFs employ random semi-orthogonal matrices, drawn…

Estimating the expectation of a real-valued function of a random variable from sample data is a critical aspect of statistical analysis, with far-reaching implications in various applications. Current methodologies typically assume…

Recent approaches for monocular 3D human pose estimation (3D HPE) have achieved leading performance by directly regressing 3D poses from 2D keypoint sequences. Despite the rapid progress in 3D HPE, existing methods are typically trained and…