Graph Attention Networks
- Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, P. Lio’, Yoshua Bengio
- Computer ScienceInternational Conference on Learning…
- 30 October 2017
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior…
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
- S. Jégou, M. Drozdzal, David Vázquez, Adriana Romero, Yoshua Bengio
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 28 November 2016
The proposed DenseNets approach achieves state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining, and has much less parameters than currently published best entries for these datasets.
Theano: A Python framework for fast computation of mathematical expressions
- Rami Al-Rfou, Guillaume Alain, Ying Zhang
- Computer ScienceArXiv
- 9 May 2016
The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed.
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
- Jure Zbontar, F. Knoll, Y. Lui
- Computer Science, MedicineArXiv
- 21 November 2018
The fastMRI dataset is introduced, a large-scale collection of both raw MR measurements and clinical MR images that can be used for training and evaluation of machine-learning approaches to MR image reconstruction.
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images
- David Vázquez, Jorge Bernal, Aaron C. Courville
- Computer Science, MedicineJournal of Healthcare Engineering
- 2 December 2016
A comparative study is performed to show that FCNs significantly outperform, without any further postprocessing, prior results in endoluminal scene segmentation, especially with respect to polyp segmentation and localization.
Inverse Cooking: Recipe Generation From Food Images
- Amaia Salvador, M. Drozdzal, Xavier Giró-i-Nieto, Adriana Romero
- Computer ScienceComputer Vision and Pattern Recognition
- 14 December 2018
An inverse cooking system that recreates cooking recipes given food images by predicting ingredients as sets by means of a novel architecture, modeling their dependencies without imposing any order, and then generates cooking instructions by attending to both image and its inferred ingredients simultaneously.
ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation
- Francesco Visin, Adriana Romero, Aaron C. Courville
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 22 November 2015
A structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks to retrieve distant dependencies, based on the recently introduced ReNet model for image classification is proposed.
Learning normalized inputs for iterative estimation in medical image segmentation
- M. Drozdzal, G. Chartrand, S. Kadoury
- Computer ScienceMedical Image Anal.
- 16 February 2017
BigBrain 3D atlas of cortical layers: Cortical and laminar thickness gradients diverge in sensory and motor cortices
- K. Wagstyl, S. Larocque, Alan C. Evans
- BiologybioRxiv
- 17 March 2019
This BigBrain cortical atlas was derived from a 3D histological model of the human brain at 20 micron isotropic resolution (BigBrain), using a convolutional neural network to segment, automatically, the cortical layers in both hemispheres and provides an unprecedented level of precision and detail.
fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning.
- F. Knoll, Jure Zbontar, Y. Lui
- Medicine, Computer ScienceRadiology: Artificial Intelligence
- 29 January 2020
A publicly available dataset containing k-space data as well as Digital Imaging and Communications in Medicine image data of knee images for accelerated MR image reconstruction using machine learning…
...
...