People

Adriana Romero

Research Scientist

I am a research scientist in Facebook AI Research (FAIR). Previously, I was a post-doctoral researcher at Montreal Institute for Learning Algorithms, advised by Prof. Yoshua Bengio. My postdoctoral research revolved around deep learning techniques to tackle biomedical challenges, such as the ones posed by imaging multi-modality, high dimensional data and graph structured data. I received my PhD from the University of Barcelona in 2015. My thesis was on assisting the training of deep neural networks with applications to computer vision, advised by Dr. Carlo Gatta. My PhD included contributions in the fields of representation learning and model compression, with applications to image classification, image segmentation and remote sensing.

Interests

Deep learning, computer vision, graphs, multi-modality, and medical imaging

Related Links

Website

Latest Publications

Inverse Cooking: Recipe Generation from Food Images

Amaia Salvador, Michal Drozdzal, Xavier Giro-i-Nieto, Adriana Romero

CVPR - June 16, 2019

Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition

Zizhao Zhang, Adriana Romero, Matthew J. Muckley, Pascal Vincent, Lin Yang, Michal Drozdzal

CVPR - June 16, 2019

GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects

Edward J. Smith, Scott Fujimoto, Adriana Romero, David Meger

ICML - June 10, 2019

Convolutional neural networks for mesh-based parcellation of the cerebral cortex

Guillem Cucurull, Konrad Wagstyl, Arantxa Casanova, Petar Velickovic, Estrid Jakobsen, Michal Drozdzal, Adriana Romero, Alan Evans, Yoshua Bengio

MIDL - March 12, 2019

On the iterative refinement of densely connected representation levels for semantic segmentation

Arantxa Casanova, Guillem Cucurull, Michal Drozdzal, Adriana Romero, Yoshua Bengio

CVPRW 2018 - June 18, 2018

Graph Attention Networks

Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio

ICLR 2018 - April 30, 2018