Gmmseg: Gaussian mixture based generative semantic segmentation models
Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier
of p (class| pixel feature). Though straightforward, this de facto paradigm neglects the …
of p (class| pixel feature). Though straightforward, this de facto paradigm neglects the …
Card: Classification and regression diffusion models
Learning the distribution of a continuous or categorical response variable y given its
covariates x is a fundamental problem in statistics and machine learning. Deep neural …
covariates x is a fundamental problem in statistics and machine learning. Deep neural …
A review of change of variable formulas for generative modeling
U Köthe - arXiv preprint arXiv:2308.02652, 2023 - arxiv.org
Change-of-variables (CoV) formulas allow to reduce complicated probability densities to
simpler ones by a learned transformation with tractable Jacobian determinant. They are thus …
simpler ones by a learned transformation with tractable Jacobian determinant. They are thus …
Score-based generative classifiers
The tremendous success of generative models in recent years raises the question whether
they can also be used to perform classification. Generative models have been used as …
they can also be used to perform classification. Generative models have been used as …
How to understand limitations of generative networks
Well-trained classifiers and their complete weight distributions provide us with a well-
motivated and practicable method to test generative networks in particle physics. We …
motivated and practicable method to test generative networks in particle physics. We …
On the practicality of deterministic epistemic uncertainty
A set of novel approaches for estimating epistemic uncertainty in deep neural networks with
a single forward pass has recently emerged as a valid alternative to Bayesian Neural …
a single forward pass has recently emerged as a valid alternative to Bayesian Neural …
Hierarchical gaussian mixture normalizing flow modeling for unified anomaly detection
Unified anomaly detection (AD) is one of the most valuable challenges for anomaly
detection, where one unified model is trained with normal samples from multiple classes …
detection, where one unified model is trained with normal samples from multiple classes …
Resampling base distributions of normalizing flows
V Stimper, B Schölkopf… - International …, 2022 - proceedings.mlr.press
Normalizing flows are a popular class of models for approximating probability distributions.
However, their invertible nature limits their ability to model target distributions whose support …
However, their invertible nature limits their ability to model target distributions whose support …
Generative classifiers as a basis for trustworthy image classification
With the maturing of deep learning systems, trustworthiness is becoming increasingly
important for model assessment. We understand trustworthiness as the combination of …
important for model assessment. We understand trustworthiness as the combination of …
Marginal post-processing of Bayesian inference products with normalizing flows and kernel density estimators
Bayesian analysis has become an indispensable tool across many different cosmological
fields, including the study of gravitational waves, the cosmic microwave background, and the …
fields, including the study of gravitational waves, the cosmic microwave background, and the …