Abhinav Agarwalla

I am a Masters student at the Robotics Institute, Carnegie Mellon University. Previously, I was working as a research assistant in Video Analytics Lab, Indian Institute of Science, advised by Prof. Venkatesh Babu, primarily on unsupervised learning and domain generalisation.

Before that, I was as a Data Scientist at Microsoft, working on improving search at Bing scale. I graduated from Indian Institute of Technology Kharagpur majoring in Mathematics and Computing.

In the past, I have had the good fortune to work with Prof. Russ Greiner, Prof. Nasir Rajpoot, Prof. Pabitra Mitra and Prof. Jayanta Mukhopadhyay on a diverse set of topic - ranging from video summarisation, motion planning for mobile robots to applying machine learning for pressing issues such as estimating insulin intake, detecting tumorous cells, etc.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Github

profile photo

I am broadly interested in machine learning and optimisation, with a special focus on problems arising in computer vision and robotics. Presently, my research is focused on unsupervised learning, semi-supervised learning, domain adaptation and transfer learning. I also enjoy developing creative AI solutions to pressing problems in healthcare.

Reviewer: ICRA 2021

Papers (* joint first authors)
3DSP Completely Self-Supervised Crowd Counting via Distribution Matching
Deepak Babu Sam*, Abhinav Agarwalla*, Jimmy Joseph, Vishwanath A. Sindagi, R. Venkatesh Babu, Vishal M. Patel
arxiv Preprint, 2020
paper / code

Existing self-supervised approaches can learn good representations, but require some labeled data to map these features to the end task of crowd density estimation. We mitigate this issue with the proposed paradigm of complete self-supervision, which does not need even a single labeled image.

3DSP Bayesian optimisation with prior reuse for motion planning in robot soccer
Abhinav Agarwalla*, Arnav Kumar Jain*, KV Manohar, Arpit Tarang Saxena, Jayanta Mukhopadhyay
CoDS - COMAD 2018

We integrate learning and motion planning for soccer playing differential drive robots using Bayesian optimisation.

3DSP Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach
Avisek Lahiri*, Abhinav Agarwalla*, Prabir Kumar Biswas
paper / code
3DSP Recurrent Memory Addressing for describing videos
Arnav Kumar Jain*, Abhinav Agarwalla*, Kumar Krishna Agrawal, Pabitra Mitra
Deep Learning in Computer Vision, CVPR 2017

In this paper, we introduce Key-Value Memory Networks to a multimodal setting and a novel key-addressing mechanism to deal with sequence-to-sequence models. The proposed model naturally decomposes the problem of video captioning into vision and language segments, dealing with them as key-value pairs.

3DSP Representation-aggregation networks for segmentation of multi-gigapixel histology images
Abhinav Agarwalla*, Muhammad Shaban, Nasir M Rajpoot
Deep Learning in Irregular Domains, BMVC 2017
paper / code

CNNs have become the preferred choice for most computer vision tasks. However, these are not best suited for multi-gigapixel resolution Whole Slide Images (WSIs) of histology slides due to large size of these images. This work address this issue with novel 2D-LSTM + CNN network for tumor segmentation.

Fork of a fork :)