People

Piotr Dollar

Research Manager

I am a research scientist at Facebook AI Research (FAIR) as of Fall 2014 with a focus on computer vision and machine learning. Prior, I spent three years at Microsoft Research in Redmond (MSR). I helped cofound Anchovi Labs (acquired by Dropbox in 2012) and was a postdoc at the Computation Vision Lab at Caltech under Pietro Perona until 2011. I received my PhD under the guidance of Serge Belongie at UCSD in 2007 and have continued doing research in vision and learning since.

Interests

Machine learning, pattern recognition, computer vision

Latest Publications

arXiv - June 19, 2021

Fast and Accurate Model Scaling

Piotr Dollár, Mannat Singh, Ross Girshick

CVPR - June 19, 2021

Boundary IoU: Improving Object-Centric Image Segmentation Evaluation

Bowen Cheng, Ross Girshick, Piotr Dollár, Alexander C. Berg, Alexander Kirillov

ECCV - July 20, 2020

Are Labels Necessary for Neural Architecture Search?

Chenxi Liu, Piotr Dollár, Kaiming He, Ross Girshick, Alan Yuille, Saining Xie

CVPR - June 14, 2020

Designing Network Design Spaces

Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, Piotr Dollár

ICCV - October 28, 2019

TensorMask: A Foundation for Dense Object Segmentation

Xinlei Chen, Ross Girshick, Kaiming He, Piotr Dollár

ICCV - October 27, 2019

Rethinking ImageNet Pre-training

Kaiming He, Ross Girshick, Piotr Dollár

ICCV - October 26, 2019

On Network Design Spaces for Visual Recognition

Ilija Radosavovic, Justin Johnson, Saining Xie, Wan-Yen Lo, Piotr Dollár

CVPR - June 18, 2019

LVIS: A Dataset for Large Vocabulary Instance Segmentation

Agrim Gupta, Piotr Dollár, Ross Girshick

CVPR - June 17, 2019

Panoptic Feature Pyramid Networks

Alexander Kirillov, Ross Girshick, Kaiming He, Piotr Dollár

CVPR - June 17, 2019

Panoptic Segmentation

Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, Piotr Dollár

CVPR 2018 - June 18, 2018

Detecting and Recognizing Human-Object Interactions

Georgia Gkioxari, Ross Girshick, Piotr Dollár, Kaiming He

CVPR 2018 - June 18, 2018

Learning to Segment Every Thing

Ronghang Hu, Piotr Dollár, Kaiming He, Trevor Darrell, Ross Girshick

CVPR 2018 - June 18, 2018

Data Distillation: Towards Omni-Supervised Learning

Ilija Radosavovic, Piotr Dollár, Ross Girshick, Georgia Gkioxari, Kaiming He

ICCV 2017 - October 22, 2017

Focal Loss for Dense Object Detection

Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollár

ICCV 2017 - October 22, 2017

Mask R-CNN

Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick

CVPR 2017 - July 21, 2017

Feature Pyramid Networks for Object Detection

Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie

CVPR 2017 - July 21, 2017

Learning Features by Watching Objects Move

Deepak Pathak, Ross Girshick, Piotr Dollár, Trevor Darrell, Bharath Hariharan

CVPR 2017 - July 21, 2017

Semantic Amodal Segmentation

Yan Zhu, Yuandong Tian, Dimitris Mexatas, Piotr Dollár

CVPR 2017 - July 21, 2017

Aggregated Residual Transformations for Deep Neural Networks

Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He

Data @ Scale - June 8, 2017

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Priya Goyal, Piotr Dollár, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, Kaiming He

ECCV - October 10, 2016

Learning to Refine Object Segments

Pedro O. Pinheiro, Tsung-Yi Lin, Ronan Collobert, Piotr Dollár

BMVC - September 18, 2016

A MultiPath Network for Object Detection

Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin, Pedro O. Pinheiro, Sam Gross, Soumith Chintala, Piotr Dollár

CVPR - June 27, 2016

Unsupervised Learning of Edges

Yin Li, Manohar Paluri, James M. Rehg, Piotr Dollár

ICLR - May 2, 2016

Metric Learning with Adaptive Density Discrimination

Oren Rippel, Manohar Paluri, Piotr Dollár, Lubomir Bourdev

NIPS - December 15, 2015

Learning to Segment Object Candidates

Pedro Oliveira, Ronan Collobert, Piotr Dollár

PAMI - February 17, 2015

What Makes for Effective Detection Proposals?

Jan Hosang, Rodrigo Benenson, Piotr Dollár, Bernt Schiele