Pedro O. Pinheiro

I am currently a research scientist at Element AI (Montreal, Canada) with a focus on computer vision and machine learning.

I received a Ph.D. from École Polytechnique Fédérale de Lausanne (EPFL) and Idiap Research Institute, under supervision of Ronan Collobert in 2017. During my studies, I spent time at Facebook AI (FAIR) working with Piotr Dollár. Previously, I graduated with a MSc. in Image and Signal Processing from Institut National des Sciences Appliquées (INSA), in France. I am originally form sunny Fortaleza, Brazil.

Email  /  Google Scholar  /  GitHub  /  LinkedIn

profile photo

Research

I'm interested in computer vision, machine learning, and their intersections. Currently, I am focused on learning with less (or no) supervision and how to efficiently leverage knowledge across different tasks.

I am also interested in transformative applications of machine learning to exposure sciences, in particular air pollution prediction.

project image

Reinforced Active Learning for Image Segmentation


Arantxa Casanova, Pedro O. Pinheiro, Negar Rostamzadeh, Christopher Pal
ICLR, 2020
paper /

project image

Neural Multisensory Scene Inference


Jae Hyun Lim, Pedro O. Pinheiro, Negar Rostamzadeh, Christopher Pal, Sungjin Ahn
NeurIPS, 2019
paper / code /

project image

Adaptive Cross-Modal Few-shot Learning


Chen Xing, Negar Rostamzadeh, Boris N. Oreshkin, Pedro O. Pinheiro
NeurIPS, 2019
paper / code /

project image

Domain-Adaptive Single-View 3D Reconstruction


Pedro O. Pinheiro, Negar Rostamzadeh, Sungjin Ahn
ICCV (oral), 2019
paper /

project image

Extending the spatial scale of land use regression models for ambient ultrafine particles using satellite images and deep convolutional neural networks


Kris Y.Hong, Pedro O. Pinheiro, Laura Minet, Marianne Hatzopoulou, Scott Weichenthal
Environmental Research Journal, 2019
paper /

project image

Predicting Global Variations in Outdoor PM2. 5 Concentrations using Satellite Images and Deep Convolutional Neural Networks


Kris Y Hong, Pedro O. Pinheiro, Scott Weichenthal
ICML Workshop for Social Good, 2019
paper /

project image

Unsupervised Domain Adaptation with Similarity Learning


Pedro O. Pinheiro
CVPR, 2018
paper /

project image

Where are the Blobs: Counting by Localization with Point Supervision


Issam Laradji, Negar Rostamzadeh, Pedro O. Pinheiro,David Vazquez. Mark Schmidt
ECCV, 2018
paper / code /

project image

Learning to Refine Object Segments


Pedro O. Pinheiro*, Tsung-Yi Lin*, Ronan Collobert, Piotr Dollar
ECCV (spotilight), 2016
paper / code /

project image

A Multipath Network for Object Detection


Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin, Pedro O. Pinheiro, Sam Gross, Soumith Chintala, Piotr Dollár
BMVC, 2016
paper / code /

project image

Learning to Segment Object Candidates


Pedro O. Pinheiro*, Ronan Collobert, Piotr Dollar
NIPS (spotlight), 2015
paper / code /

project image

Phrase-Based Image Captioning


Rémi Lebret*, Pedro O. Pinheiro*, Ronan Collobert
ICML, 2015
paper /

project image

From Image-level to Pixel-level Labeling with Convolutional Networks


Pedro O. Pinheiro, Ronan Collobert
CVPR, 2015
paper /

project image

Recurrent Convolutional Neural Networks for Scene Labeling


Pedro O. Pinheiro, Ronan Collobert
ICML, 2014
paper /





Design and source code from Jon Barron's website and Leonid Keselman's Jekyll fork of it.