Search Results for author: Bas Peters

Found 12 papers, 0 papers with code

Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface data

no code implementations30 Jun 2024 Bas Peters, Eldad Haber, Keegan Lensink

Examples in hyperspectral land-use classification, airborne geophysical surveying, and seismic imaging illustrate that we can input large data volumes in one chunk and do not need to work on small patches, use dimensionality reduction, or employ methods that classify a patch to a single central pixel.

Dimensionality Reduction Seismic Imaging

Paired Autoencoders for Inverse Problems

no code implementations21 May 2024 Matthias Chung, Emma Hart, Julianne Chung, Bas Peters, Eldad Haber

We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation.

InvertibleNetworks.jl: A Julia package for scalable normalizing flows

no code implementations20 Dec 2023 Rafael Orozco, Philipp Witte, Mathias Louboutin, Ali Siahkoohi, Gabrio Rizzuti, Bas Peters, Felix J. Herrmann

InvertibleNetworks. jl is a Julia package designed for the scalable implementation of normalizing flows, a method for density estimation and sampling in high-dimensional distributions.

Density Estimation Seismic Imaging

CQnet: convex-geometric interpretation and constraining neural-network trajectories

no code implementations9 Feb 2023 Bas Peters

We introduce CQnet, a neural network with origins in the CQ algorithm for solving convex split-feasibility problems and forward-backward splitting.

Point-to-set distance functions for weakly supervised segmentation

no code implementations27 Jul 2020 Bas Peters

We illustrate the capabilities in case of a) one or more classes do not have any annotation; b) there is no annotation at all; c) there are bounding boxes.

Object Segmentation +2

Deep connections between learning from limited labels & physical parameter estimation -- inspiration for regularization

no code implementations17 Mar 2020 Bas Peters

We show that explicit regularization of model parameters in PDE constrained optimization translates to regularization of the network output.

Fully reversible neural networks for large-scale surface and sub-surface characterization via remote sensing

no code implementations16 Mar 2020 Bas Peters, Eldad Haber, Keegan Lensink

The large spatial/frequency scale of hyperspectral and airborne magnetic and gravitational data causes memory issues when using convolutional neural networks for (sub-) surface characterization.

Change Detection

Symmetric block-low-rank layers for fully reversible multilevel neural networks

no code implementations14 Dec 2019 Bas Peters, Eldad Haber, Keegan Lensink

Factors that limit the size of the input and output of a neural network include memory requirements for the network states/activations to compute gradients, as well as memory for the convolutional kernels or other weights.

Video Segmentation Video Semantic Segmentation

Fully Hyperbolic Convolutional Neural Networks

no code implementations24 May 2019 Keegan Lensink, Bas Peters, Eldad Haber

However, their application to problems with high dimensional input and output, such as high-resolution image and video segmentation or 3D medical imaging, has been limited by various factors.

Depth Estimation General Classification +6

Neural-networks for geophysicists and their application to seismic data interpretation

no code implementations27 Mar 2019 Bas Peters, Eldad Haber, Justin Granek

Neural-networks have seen a surge of interest for the interpretation of seismic images during the last few years.

Automatic classification of geologic units in seismic images using partially interpreted examples

no code implementations12 Jan 2019 Bas Peters, Justin Granek, Eldad Haber

Tests on seismic images and interpretation information from the Sea of Ireland show that we obtain high-quality predicted interpretations from a small number of large seismic images.

General Classification Segmentation +2

Multi-resolution neural networks for tracking seismic horizons from few training images

no code implementations26 Dec 2018 Bas Peters, Justin Granek, Eldad Haber

Our networks learn from a small number of large seismic images without creating patches.

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