Assistant Professor
Associate Director, ML@GT
School of Interactive Computing
CODA room S1181B
Email: zkira at gatech dot edu
 

Latest News [Older]

Recent Talks: OoD/Calibration and Distribution Shift, Continual Learning



03/2022 Nature Machine Intelligence paper on biological underpinnings of lifelong learning
03/2022 Excited to be an Action Editor for the new Transactions on ML Research (TMLR)
03/2022 Two CVPR papers on unbiased teacher v2 and cross-modal models for captioning.
02/2022 Two ICRA papers on imbalanced semantic seg and 6D pose estimation for grasping.
01/2022 Funding from IRIM/IPaT for multi-modal continual learning, with Diyi Yang.
01/2022 Talks at UIUC, Vanderbilt, UW, and UTSA.
09/2021 Two NeurIPS Spotlights (<3% accept) on principled calibration and Habitat 2.0 (w/ FB).
07/2021 ICCV paper on data-free incremental learning (no replay!).
07/2021 Area Chair for ICLR 2022.
06/2021 Press for Habitat 2.0: CNET | TechCrunch | VentureBeat | Wired (ME) | Ynet
06/2021 IROS paper on distributed spatial registration and perception.
05/2021 Invited talks at Google and Microsoft AI.
05/2021 Funding for Phase II of the DARPA LwLL program.
04/2021 IJCNN paper on semi-supervised continual learning.
05/2021 Funding for Phase II of the DARPA L2M program.
03/2021 Two ICRA papers (one RA-L too) on RoboVLN and 3D learnable region growing!
02/2021 ICLR paper on SoA semi-supervised object detection (~17% mAP w/ 0.5% data!) [project]
02/2021 Co-organizing the CVPR workshop on Learning from Limited and Imperfect Data (L2ID).
02/2021 Code release for our FeatMatch semi-supervised learning paper [paper] [code]

2020 We had 1 AAAI, 2 ICRA, 3 CVPR, 2 ECCV papers. We partnered with Facebook on a co-teaching program, I served as Area Chair for NeurIPS, and I gave invited talks at the VL3, Agriculture Vision, and ULAD-2020 Workshops.
-

2019 We had 3 ICLR, 1 ICRA, 1 CVPR, 1 Oral ICCV, 2 journal, 1 WACV, and ICLR/IROS workshop papers. We received funding from DARPA LwLL and Samsung.

2018 We had a ICLR, CVPR, WACV, NeurIPS Continual Learning Workshop, and one journal paper. We received new funding from DARPA L2M and ONR.

08/2018 Assistant Professor!

About Me

I am an Assistant Professor at the School of Interactive Computing in the College of Computing. I am also affiliated with the Georgia Tech Research Institute and 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.

I lead the RobotIcs Perception and Learning (RIPL) lab. 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. I am especially interested in moving beyond supervised learning (un/semi/self-supervised and continual/lifelong learning) as well as distributed perception (multi-modal fusion, learning to incorporate information across a group of robots, etc.).