Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier
of p (class| pixel feature). Though straightforward, this de facto paradigm neglects the …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

With the maturing of deep learning systems, trustworthiness is becoming increasingly
important for model assessment. We understand trustworthiness as the combination of …

Bayesian analysis has become an indispensable tool across many different cosmological
fields, including the study of gravitational waves, the cosmic microwave background, and the …