Recent years have seen a tremendous growth in both the capability and
po...
Reliable uncertainty quantification in deep neural networks is very cruc...
This paper presents a fast and principled approach for solving the visua...
Split computing has emerged as a recent paradigm for implementation of
D...
This paper presents a fast, principled approach for detecting anomalous ...
This paper introduces supervised contrastive active learning (SCAL) by
l...
This paper presents simple and efficient methods to mitigate sampling bi...
In this paper, we propose an approach to improve image captioning soluti...
In this paper, we study the impact of motion blur, a common quality flaw...
This brief sketches initial progress towards a unified energy-based solu...
Obtaining reliable and accurate quantification of uncertainty estimates ...
This paper presents a principled approach for detecting out-of-distribut...
Transparency of algorithmic systems entails exposing system properties t...
Bayesian deep neural networks (DNN) provide a mathematically grounded
fr...
This paper introduces Tree-Pyramidal Adaptive Importance Sampling (TP-AI...
Data poisoning attacks compromise the integrity of machine-learning mode...
We present a principled approach for detecting out-of-distribution (OOD)...
Variational inference for Bayesian deep neural networks (DNNs) requires
...
Deep neural networks (DNNs) provide state-of-the-art results for a multi...
Uncertainty estimation in deep neural networks is essential for designin...