12 citations · 21 across the 16 of their papers we have counts for
13 papers · 1 filter
Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture
Mehraveh Javan, Matthew Toews, Marco Pedersoli
Downsampling layers, including pooling and strided convolutions, are crucial components of the convolutional neural network architecture that determine both the granularity/scale o…
PSDNet: Determination of Particle Size Distributions Using Synthetic Soil Images and Convolutional Neural Networks
Javad Manashti, Pouyan Pirnia, Alireza Manashty +3
This project aimed to determine the grain size distribution of granular materials from images using convolutional neural networks. The application of ConvNet and pretrained ConvNet…
Comparing PSDNet, pretrained networks, and traditional feature extraction for predicting the particle size distribution of granular materials from photographs
Javad Manashti, François Duhaime, Matthew F. Toews +2
This study aims to evaluate PSDNet, a series of convolutional neural networks (ConvNets) trained with photographs to predict the particle size distribution of granular materials. N…
U(1) Symmetry-breaking Observed in Generic CNN Bottleneck Layers
Louis-François Bouchard, Mohsen Ben Lazreg, Matthew Toews
We report on a novel model linking deep convolutional neural networks (CNN) to biological vision and fundamental particle physics. Information propagation in a CNN is modeled via a…
Registering Image Volumes using 3D SIFT and Discrete SP-Symmetry
Laurent Chauvin, William Wells, Matthew Toews
This paper proposes to extend local image features in 3D to include invariance to discrete symmetry including inversion of spatial axes and image contrast. A binary feature sign $s…
GPU optimization of the 3D Scale-invariant Feature Transform Algorithm and a Novel BRIEF-inspired 3D Fast Descriptor
Jean-Baptiste Carluer, Laurent Chauvin, Jie Luo +4
This work details a highly efficient implementation of the 3D scale-invariant feature transform (SIFT) algorithm, for the purpose of machine learning from large sets of volumetric…
Curating Subject ID Labels using Keypoint Signatures
Laurent Chauvin, Matthew Toews
Subject ID labels are unique, anonymized codes that can be used to group all images of a subject while maintaining anonymity. ID errors may be inadvertently introduced manually err…
Large Scale Indexing of Generic Medical Image Data using Unbiased Shallow Keypoints and Deep CNN Features
L. Chauvin, M. Ben Lazreg, J. B. Carluer +2
We propose a unified appearance model accounting for traditional shallow (i.e. 3D SIFT keypoints) and deep (i.e. CNN output layers) image feature representations, encoding respecti…
Keypoint Transfer for Fast Whole-Body Segmentation
Christian Wachinger, Matthew Toews, Georg Langs +2
We introduce an approach for image segmentation based on sparse correspondences between keypoints in testing and training images. Keypoints represent automatically identified disti…
A Feature-Driven Active Framework for Ultrasound-Based Brain Shift Compensation
Jie Luo, Matt Toews, Ines Machado +10
A reliable Ultrasound (US)-to-US registration method to compensate for brain shift would substantially improve Image-Guided Neurological Surgery. Developing such a registration met…
On the Applicability of Registration Uncertainty
Jie Luo, Alireza Sedghi, Karteek Popuri +8
Estimating the uncertainty in (probabilistic) image registration enables, e.g., surgeons to assess the operative risk based on the trustworthiness of the registered image data. If…
Multi-modal analysis of genetically-related subjects using SIFT descriptors in brain MRI
Kuldeep Kumar, Laurent Chauvin, Mathew Toews +2
So far, fingerprinting studies have focused on identifying features from single-modality MRI data, which capture individual characteristics in terms of brain structure, function, o…
Probabilistic Diffeomorphic Registration: Representing Uncertainty
Demian Wassermann, Matt Toews, Marc Niethammer +1
This paper presents a novel mathematical framework for representing uncertainty in large deformation diffeomorphic image registration. The Bayesian posterior distribution over the…