555 citations · 806 across the 17 of their papers we have counts for
20 papers
Active 3D Shape Reconstruction from Vision and Touch
Edward J. Smith, David Meger, Luis Pineda +4
Humans build 3D understandings of the world through active object exploration, using jointly their senses of vision and touch. However, in 3D shape reconstruction, most recent prog…
Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver
Levent Sagun, Caglar Gulcehre, Adriana Romero +2
Science meets Engineering in Deep Learning took place in Vancouver as part of the Workshop section of NeurIPS 2019. As organizers of the workshop, we created the following report i…
Active MR k-space Sampling with Reinforcement Learning
Luis Pineda, Sumana Basu, Adriana Romero +2
Deep learning approaches have recently shown great promise in accelerating magnetic resonance image (MRI) acquisition. The majority of existing work have focused on designing bette…
3D Shape Reconstruction from Vision and Touch
Edward J. Smith, Roberto Calandra, Adriana Romero +4
When a toddler is presented a new toy, their instinctual behaviour is to pick it upand inspect it with their hand and eyes in tandem, clearly searching over its surface to properly…
Learning to adapt class-specific features across domains for semantic segmentation
Mikel Menta, Adriana Romero, Joost van de Weijer
Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capabilit…
On the Evaluation of Conditional GANs
Terrance DeVries, Adriana Romero, Luis Pineda +2
Conditional Generative Adversarial Networks (cGANs) are finding increasingly widespread use in many application domains. Despite outstanding progress, quantitative evaluation of su…
Elucidating image-to-set prediction: An analysis of models, losses and datasets
Luis Pineda, Amaia Salvador, Michal Drozdzal +1
In this paper, we identify an important reproducibility challenge in the image-to-set prediction literature that impedes proper comparisons among published methods, namely, researc…
Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
Zizhao Zhang, Adriana Romero, Matthew J. Muckley +3
The goal of MRI reconstruction is to restore a high fidelity image from partially observed measurements. This partial view naturally induces reconstruction uncertainty that can onl…
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Edward J. Smith, Scott Fujimoto, Adriana Romero +1
Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined…
Inverse Cooking: Recipe Generation from Food Images
Amaia Salvador, Michal Drozdzal, Xavier Giro-i-Nieto +1
People enjoy food photography because they appreciate food. Behind each meal there is a story described in a complex recipe and, unfortunately, by simply looking at a food image we…
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
Jure Zbontar, Florian Knoll, Anuroop Sriram +24
Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRI possible in applicati…
On the iterative refinement of densely connected representation levels for semantic segmentation
Arantxa Casanova, Guillem Cucurull, Michal Drozdzal +2
State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided convolutions or succ…
Graph Attention Networks
Petar Veličković, Guillem Cucurull, Arantxa Casanova +3
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the short…
Image Segmentation by Iterative Inference from Conditional Score Estimation
Adriana Romero, Michal Drozdzal, Akram Erraqabi +2
Inspired by the combination of feedforward and iterative computations in the virtual cortex, and taking advantage of the ability of denoising autoencoders to estimate the score of…
Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
Michal Drozdzal, Gabriel Chartrand, Eugene Vorontsov +6
In this paper, we introduce a simple, yet powerful pipeline for medical image segmentation that combines Fully Convolutional Networks (FCNs) with Fully Convolutional Residual Netwo…
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images
David Vázquez, Jorge Bernal, F. Javier Sánchez +5
Colorectal cancer (CRC) is the third cause of cancer death worldwide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for…
Diet Networks: Thin Parameters for Fat Genomics
Adriana Romero, Pierre Luc Carrier, Akram Erraqabi +7
Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training exam…
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
Simon Jégou, Michal Drozdzal, David Vazquez +2
State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampli…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Francesco Visin, Marco Ciccone, Adriana Romero +5
We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks…