no code implementations • 13 Nov 2023 • Surojit Saha, Sarang Joshi, Ross Whitaker
However, the VAE's known failure to match the aggregate posterior often results in \emph{pockets/holes} in the latent distribution (i. e., a failure to match the prior) and/or \emph{posterior collapse}, which is associated with a loss of information in the latent space.
1 code implementation • 19 Apr 2023 • Mingzhen Shao, Tolga Tasdizen, Sarang Joshi
This study explores the resilience of a variety of deep homography estimation models to domain shifts, revealing that the network architecture itself is not a contributing factor to this remarkable adaptability.
1 code implementation • 6 Apr 2023 • Haocheng Dai, Michael Penwarden, Robert M. Kirby, Sarang Joshi
Neural operator learning as a means of mapping between complex function spaces has garnered significant attention in the field of computational science and engineering (CS&E).
1 code implementation • 6 Mar 2022 • Haocheng Dai, Martin Bauer, P. Thomas Fletcher, Sarang Joshi
The goal of diffusion-weighted magnetic resonance imaging (DWI) is to infer the structural connectivity of an individual subject's brain in vivo.
1 code implementation • 2 Apr 2021 • Amanpreet Singh, Martin Bauer, Sarang Joshi
Optimal Mass Transport (OMT) is a well studied problem with a variety of applications in a diverse set of fields ranging from Physics to Computer Vision and in particular Statistics and Data Science.
no code implementations • 22 Jul 2018 • Markus D. Foote, Blake E. Zimmerman, Amit Sawant, Sarang Joshi
We use this deep network to approximate the nonlinear inverse of a diffeomorphic deformation composed with radiographic projection.
no code implementations • 19 May 2018 • Line Kuhnel, Tom Fletcher, Sarang Joshi, Stefan Sommer
Given data, deep generative models, such as variational autoencoders (VAE) and generative adversarial networks (GAN), train a lower dimensional latent representation of the data space.
no code implementations • 31 May 2017 • Stefan Sommer, Alexis Arnaudon, Line Kuhnel, Sarang Joshi
We present an inference algorithm and connected Monte Carlo based estimation procedures for metric estimation from landmark configurations distributed according to the transition distribution of a Riemannian Brownian motion arising from the Large Deformation Diffeomorphic Metric Mapping (LDDMM) metric.