Search Results for author: Sarang Joshi

Found 8 papers, 4 papers with code

Matching aggregate posteriors in the variational autoencoder

no code implementations13 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.

Analyzing the Domain Shift Immunity of Deep Homography Estimation

1 code implementation19 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.

Homography Estimation Transfer Learning

Neural Operator Learning for Ultrasound Tomography Inversion

1 code implementation6 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).

Operator learning

Modeling the Shape of the Brain Connectome via Deep Neural Networks

1 code implementation6 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.

Physics Informed Convex Artificial Neural Networks (PICANNs) for Optimal Transport based Density Estimation

1 code implementation2 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.

Density Estimation

Latent Space Non-Linear Statistics

no code implementations19 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.

Bridge Simulation and Metric Estimation on Landmark Manifolds

no code implementations31 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.