Research
I'm interested in algorithms for visual perception
(object recognition, localization, segmentation, pose
estimation, ...), representation learning
(pre-training networks using strong supervision, weak
supervision, or no supervision at all), and the interaction of
vision and language. My work explores
topics in computer vision and machine/deep/statistical learning.
About me / bio
Ross Girshick is a Distinguished Research Scientist at the Allen Institute for Artificial Intelligence (AI2). He
received a PhD in computer science in 2012 from the University of Chicago while working with Pedro Felzenszwalb. Before
joining AI2, Ross was a Research Scientist in Meta's Fundamental AI Research (FAIR) team working on computer vision and
machine learning (2015-2023), a Researcher at Microsoft Research (2014-2015), and a postdoc at the University of
California, Berkeley, where he was advised by Jitendra Malik and Trevor Darrell (2012-2014). His interests include
representation learning and systems for solving computer vision problems that exhibit broad generalization. He received
the 2017 PAMI Young Researcher Award and the 2017, 2021, and 2023 PAMI Mark Everingham Prizes for his contributions to
open source software and datasets. Ross is well-known for developing the R-CNN (Region-based Convolutional Neural
Network) approach to object detection, and, in 2017, Ross received the Marr Prize at ICCV for "Mask R-CNN". Outside of
research, Ross is usually rock climbing and trying to send his latest project.
Journal reviewing note: Please do not invite me to review unless you have asked me via a personal message beforehand (though I will most likely decline). I receive many unsolicited requests per week, which I simply delete without reading due to the volume.