Home Publications

Harkirat Behl


profile-pic


Senior Researcher
Microsoft Research

Interests
Machine Learning, Computer Vision and Optimization

Education
PhD, University of Oxford, 2021
BTech, Indian Institute of Technology (IIT) Kanpur, 2018

Feel free to get in touch for part/full-time internship at MSR

 

Publications

Neural-Sim: Learning to Generate Training Data with NeRF
Yunhao Ge, Harkirat Behl, Jiashu Xu, Suriya Gunasekar, Neel Joshi, Yale Song, Xin Wang, Laurent Itti, and Vibhav Vineet
ECCV 2022: Proceedings of European Conference on Computer Vision
     

Scaling the Convex Barrier with Sparse Dual Solvers
Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip Torr, M. Pawan Kumar
JMLR 2022: Journal of Machine Learning Research
     

Overcoming the Convex Barrier for Simplex Inputs
Harkirat Singh Behl, M. Pawan Kumar, Philip Torr, Krishnamurthy (Dj) Dvijotham
NeurIPS 2021: Advances in Neural Information Processing Systems
     

Scaling the Convex Barrier with Active Sets
Harkirat Singh Behl*, Alessandro De Palma*, Rudy Bunel, Philip Torr, M. Pawan Kumar
ICLR 2021: Proceedings of International Conference on Learning Representations
       

Progressive Skeletonization: Trimming more fat from a network at initialization
Pau Jorge, Amartya Sanyal, Harkirat Singh Behl, Philip Torr, Gregory Rogez, Puneet Dokania
ICLR 2021: Proceedings of International Conference on Learning Representations
       

STEER: Simple Temporal Regularization For Neural ODEs
Arnab Ghosh, Harkirat Singh Behl, Emilien Dupont, Philip Torr, Vinay Namboodiri
NeurIPS 2020: Advances in Neural Information Processing Systems
     

AutoSimulate: (Quickly) Learning Synthetic Data Generation
Harkirat Singh Behl, Atılım Güneş Baydin, Ran Gal, Philip Torr, Vibhav Vineet
ECCV 2020: Proceedings of European Conference on Computer Vision
       

Meta-Learning Deep Visual Words for Fast Video Object Segmentation
Harkirat Singh Behl, Mohammad Najafi, Anurag Arnab, Philip Torr
IROS 2020: Proceedings of International Conference on Intelligent Robots and Systems (Oral)
NeurIPS 2019: NeurIPS Workshop on Machine Learning for Autonomous Driving (Oral)
     

 

Alpha MAML: Adaptive Model-Agnostic Meta-Learning
Harkirat Singh Behl, Atılım Güneş Baydin, Philip Torr
ICML 2019: International Conference on Machine Learning Automated Machine Learning Workshop
       

Incremental Tube Construction for Human Action Detection
Harkirat Singh Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip Torr
BMVC 2018: Proceedings of British Machine Vision Conference