NEWS: I have accepted an offer at the School of Interactive Computing in the CoC to join as Assistant Professor in the Fall! I am looking for students for the following areas, all of them focusing on machine/deep learning for perception:

  1. Lifelong/Continual Learning and Object Discovery: We are investigating various aspects of lifelong learning, including goal-driven perception, attentional mechanisms, and object discovery. Some of this involves working with neuroscientists to understand what learning principles we can leverage when studying these methods. See our ICLR and other papers for past work we'd like to apply to large-scale robotics datasets.
  2. Distributed and Multi-Modal Perception: Integration of information from multiple sensor modalities in a principled way when using deep learning, including when a heterogeneous set of sensors are on different platforms.
If you are a student at GT and interested, feel free to email me (see address at bottom) with resume/CV and a description of your experience and why you are interested.

I am currently a Senior Research Scientist at the Georgia Tech Research Institute, where I lead a group of researchers as the chief of the Machine Learning and Analytics branch. I am also Adjunct in the School of Interactive Computing and work with several faculty and Ph.D. students, as well as serve as an Associate Director of ML@GT which is the machine learning center recently created at Georgia Tech. Previously I was a Research Scientist at SRI International Sarnoff in Princeton, and before that received my Ph.D. in 2010 with Professor Ron Arkin as my advisor. My areas of research specifically focus on the intersection of learning methods for sensor processing and robotics, developing novel machine learning algorithms and formulations towards solving some of the more difficult perception problems in these areas.



Pytorch code release for our clustering work on github


CVPR Deep-Vision Workshop paper on a new probabilistic deep learning clustering formulation [arxiv]


News article about new DARPA lifelong learning project


Blog post about our CVPR paper


Accepted IJCNN paper: Learning to Cluster for Proposal-Free Instance Segmentation [arxiv]


Accepted CVPR paper: Higher-Order Object Interactions for Video Understanding [arxiv]


Accepted ICLR paper (in top 7% of reviews!) for Learning to Cluster paper