Search Results for author:
Found 48 papers, 27 papers with code
TRADE: Transfer of Distributions between External Conditions with Normalizing Flows
Despite the relevance of these applications, existing solutions are unsatisfactory as they require severely restricted model architectures or rely on backward training, which is prone to unstable training.
Analyzing Generative Models by Manifold Entropic Metrics
Good generative models should not only synthesize high quality data, but also utilize interpretable representations that aid human understanding of their behavior.
Learning Distances from Data with Normalizing Flows and Score Matching
Density-based distances (DBDs) offer an elegant solution to the problem of metric learning.
Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors
We believe that level 1 (AdEx on a unified dataset) should be added to any OOD detector to see the limitations.
Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigation
Recent advances in probabilistic deep learning enable efficient amortized Bayesian inference in settings where the likelihood function is only implicitly defined by a simulation program (simulation-based inference; SBI).
DALSA: Domain Adaptation for Supervised Learning From Sparsely Annotated MR Images
We propose a new method that employs transfer learning techniques to effectively correct sampling selection errors introduced by sparse annotations during supervised learning for automated tumor segmentation.
On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows
In addition, we show that volume-preserving normalizing flows are not universal, what distribution they learn instead, and how to fix their expressivity.
Learning Distributions on Manifolds with Free-Form Flows
We propose Manifold Free-Form Flows (M-FFF), a simple new generative model for data on manifolds.
Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning
In this work, we analyze the conditions under which information about the context of an input $X$ can improve the predictions of deep learning models in new domains.
Consistency Models for Scalable and Fast Simulation-Based Inference
Simulation-based inference (SBI) is constantly in search of more expressive and efficient algorithms to accurately infer the parameters of complex simulation models.
Free-form Flows: Make Any Architecture a Normalizing Flow
Normalizing Flows are generative models that directly maximize the likelihood.
Sensitivity-Aware Amortized Bayesian Inference
In this work, we propose sensitivity-aware amortized Bayesian inference (SA-ABI), a multifaceted approach to efficiently integrate sensitivity analyses into simulation-based inference with neural networks.
Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
We propose a method to improve the efficiency and accuracy of amortized Bayesian inference by leveraging universal symmetries in the joint probabilistic model of parameters and data.
Application-driven Validation of Posteriors in Inverse Problems
Current deep learning-based solutions for image analysis tasks are commonly incapable of handling problems to which multiple different plausible solutions exist.
A Review of Change of Variable Formulas for Generative Modeling
Change-of-variables (CoV) formulas allow to reduce complicated probability densities to simpler ones by a learned transformation with tractable Jacobian determinant.
BayesFlow: Amortized Bayesian Workflows With Neural Networks
Modern Bayesian inference involves a mixture of computational techniques for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows for data analysis.
On the Convergence Rate of Gaussianization with Random Rotations
Gaussianization is a simple generative model that can be trained without backpropagation.
Lifting Architectural Constraints of Injective Flows
Normalizing Flows explicitly maximize a full-dimensional likelihood on the training data.
Training Invertible Neural Networks as Autoencoders
Autoencoders are able to learn useful data representations in an unsupervised matter and have been widely used in various machine learning and computer vision tasks.
Unsupervised Domain Transfer with Conditional Invertible Neural Networks
Synthetic medical image generation has evolved as a key technique for neural network training and validation.
Finding Competence Regions in Domain Generalization
We investigate a "learning to reject" framework to address the problem of silent failures in Domain Generalization (DG), where the test distribution differs from the training distribution.
JANA: Jointly Amortized Neural Approximation of Complex Bayesian Models
This work proposes ``jointly amortized neural approximation'' (JANA) of intractable likelihood functions and posterior densities arising in Bayesian surrogate modeling and simulation-based inference.
Towards Learned Emulation of Interannual Water Isotopologue Variations in General Circulation Models
Simulating abundances of stable water isotopologues, i. e. molecules differing in their isotopic composition, within climate models allows for comparisons with proxy data and, thus, for testing hypotheses about past climate and validating climate models under varying climatic conditions.
Neural Superstatistics for Bayesian Estimation of Dynamic Cognitive Models
Our results show that the deep learning approach is very efficient in capturing the temporal dynamics of the model.
Whitening Convergence Rate of Coupling-based Normalizing Flows
For the first time, we make a quantitative statement about this kind of convergence: We prove that all coupling-based normalizing flows perform whitening of the data distribution (i. e. diagonalize the covariance matrix) and derive corresponding convergence bounds that show a linear convergence rate in the depth of the flow.
Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data
We use a self-supervised feature extractor trained on the auxiliary dataset and train a normalizing flow on the extracted features by maximizing the likelihood on in-distribution data and minimizing the likelihood on the contrastive dataset.
Content-Aware Differential Privacy with Conditional Invertible Neural Networks
Manipulation of the latent space leads to a modified image while preserving important details.
Towards Multimodal Depth Estimation from Light Fields
We argue that this is due current methods only considering a single "true" depth, even when multiple objects at different depths contributed to the color of a single pixel.
Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks
Neural density estimators have proven remarkably powerful in performing efficient simulation-based Bayesian inference in various research domains.
Conditional Invertible Neural Networks for Diverse Image-to-Image Translation
We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images.
Benchmarking Invertible Architectures on Inverse Problems
Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems.
Invertible Neural Networks for Uncertainty Quantification in Photoacoustic Imaging
Multispectral photoacoustic imaging (PAI) is an emerging imaging modality which enables the recovery of functional tissue parameters such as blood oxygenation.
Learning Robust Models Using The Principle of Independent Causal Mechanisms
Standard supervised learning breaks down under data distribution shift.
OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany
Mathematical models in epidemiology are an indispensable tool to determine the dynamics and important characteristics of infectious diseases.
Generative Classifiers as a Basis for Trustworthy Image Classification
Generative classifiers (GCs) are a promising class of models that are said to naturally accomplish these qualities.
Amortized Bayesian model comparison with evidential deep learning
This makes the method particularly effective in scenarios where model fit needs to be assessed for a large number of datasets, so that per-dataset inference is practically infeasible. Finally, we propose a novel way to measure epistemic uncertainty in model comparison problems.
BayesFlow: Learning complex stochastic models with invertible neural networks
In addition, our method incorporates a summary network trained to embed the observed data into maximally informative summary statistics.
Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
In this work, firstly, we develop the theory and methodology of IB-INNs, a class of conditional normalizing flows where INNs are trained using the IB objective: Introducing a small amount of {\em controlled} information loss allows for an asymptotically exact formulation of the IB, while keeping the INN's generative capabilities intact.
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
Furthermore, the recovered informative latent variables will be in one-to-one correspondence with the true latent variables of the generating process, up to a trivial component-wise transformation.
Out of distribution detection for intra-operative functional imaging
Multispectral optical imaging is becoming a key tool in the operating room.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Conditional Invertible Neural Networks for Guided Image Generation
In this work, we address the task of natural image generation guided by a conditioning input.
Object Segmentation using Pixel-wise Adversarial Loss
Recent deep learning based approaches have shown remarkable success on object segmentation tasks.
Guided Image Generation with Conditional Invertible Neural Networks
We demonstrate these properties for the tasks of MNIST digit generation and image colorization.
HINT: Hierarchical Invertible Neural Transport for Density Estimation and Bayesian Inference
Many recent invertible neural architectures are based on coupling block designs where variables are divided in two subsets which serve as inputs of an easily invertible (usually affine) triangular transformation.
The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning
Unlike seeded watershed, the algorithm can accommodate not only attractive but also repulsive cues, allowing it to find a previously unspecified number of segments without the need for explicit seeds or a tunable threshold.
Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks
Assessment of the specific hardware used in conjunction with such algorithms, however, has not properly addressed the possibility that the problem may be ill-posed.
Analyzing Inverse Problems with Invertible Neural Networks
Often, the forward process from parameter- to measurement-space is a well-defined function, whereas the inverse problem is ambiguous: one measurement may map to multiple different sets of parameters.
Learned Watershed: End-to-End Learning of Seeded Segmentation
Learned boundary maps are known to outperform hand- crafted ones as a basis for the watershed algorithm.
