Ajay Unagar

MSc Student

ETH Zurich

Biography

Hi! I’m a final year MSc student studying Computational Science at ETH Zurich. My research interests lie in building adaptive intelligent systems which are aware of the 3D world around them and can use perception capabilities to make decisions. Towards this goal, I am interested in the topics of 3D Vision, Reinforcement Learning, and Continual Learning. Apart from gaining theoretical understanding of these topics, I also enjoy applying them to real-world robotics tasks.

Before starting my masters study, I finished my undergraduate at IIT Roorkee in India. Just after my undergraduate, I worked at ZS Associates as a Data Scientist for 2 years. I focused on many problems in healthcare domain including patient disease progression modeling, multi-channel marketing optimization, and real-time analytics.

Interests

3D Vision
Reinforcement Learning
Continual Learning
Robotics
Theory of Machine Learning

Education

MSc in Computational Science (Specialization in Robotics), 2021

ETH Zurich
BTech in Civil Engineering (Minor in Computer Science), 2017

IIT Roorkee, India

News

01/2021	Our paper "Back to the feature" has been accepted to CVPR 2021! It is on arxiv.
12/2020	Finished a semester project with IBM Research. My project report is online
11/2020	Our work on "Battery calibration using Deep RL" has been accepted at ML4Eng workshop at NeurIPS 2020. The talk is available online.
10/2020	Submitted my first main conference paper at CVPR 2021! Exciting times
07/2020	Started my semester project with the Digital Pathology team at IBM research, Zurich
06/2020	Started working as a Research Assistant with IMS Lab led by Prof. Olga Fink
06/2020	We finished 2nd in "Visual Localization for Autonomous Vehicle" competition organized by VisLocOdomMap workshop at CVPR 2020. Our talk is available online.
09/2019	Started my MSc at ETH Zurich!

Publications

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

CVPR'21

PE Sarlin, Ajay Unagar, M Larsson, H Germain, C Toft, V Larsson, M Pollefeys, V Lepetit, L Hammarstrand, F Kahl, T Sattler

Battery Model Calibration with Deep Reinforcement Learning

NeurIPS'20 Workshop & Energies Journal

Ajay Unagar, Yaun Tian, Manuel Arias Chao, Olga Fink

6-DoF Pose Refinement via Sparse-to-Dense Feature-Metric Optimization

CVPR'20 Workshop

Ajay Unagar, Philipp Lindenberger, Nickolaos Tselepidis, Paul-Edouard Sarlin

Experience

Research Assistant

Intelligent Maintenance Systems Lab, ETH Zurich

Jun 2020 – Present Zurich

Worked on battery model calibration using reinforcement learning project. Resulted in publication at NeurIPS 2020 workshop and full paper submitted to Energies journal.

Masters Project Intern

IBM Research, Zurich

Jun 2020 – Dec 2020 Zurich

Worked on continual learning for image classification in digital pathology. Developed a method which remember the past knowledge via distillation. This method works in replay-free task-incremental setting.

Machine Learning Engineer

Trexquant Investments

Oct 2017 – Oct 2020 Remote

Worked on building trading strategies using alpha signals from many sources. Applied techniques for filtering useful trading signals and combining them to make profitable strategies.