4 citations · 9 across the 6 of their papers we have counts for
11 papers
Point-to-set distance functions for weakly supervised segmentation
Bas Peters
When pixel-level masks or partial annotations are not available for training neural networks for semantic segmentation, it is possible to use higher-level information in the form o…
Fully reversible neural networks for large-scale 3D seismic horizon tracking
Bas Peters, Eldad Haber
Tracking a horizon in seismic images or 3D volumes is an integral part of seismic interpretation. The last few decades saw progress in using neural networks for this task, starting…
Deep connections between learning from limited labels & physical parameter estimation -- inspiration for regularization
Bas Peters
Recently established equivalences between differential equations and the structure of neural networks enabled some interpretation of training of a neural network as partial-differe…
Fully reversible neural networks for large-scale surface and sub-surface characterization via remote sensing
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 cha…
Symmetric block-low-rank layers for fully reversible multilevel neural networks
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 t…
Fully Hyperbolic Convolutional Neural Networks
Keegan Lensink, Bas Peters, Eldad Haber
Convolutional Neural Networks (CNN) have recently seen tremendous success in various computer vision tasks. However, their application to problems with high dimensional input and o…