Abhinav Agarwalla
I am a Machine Learning Research Engineer at Neural Magic.
Previously, I worked at Argo AI as a Research Engineer. Before that, I was a Masters student at the Robotics Institute, Carnegie Mellon University, where I worked with Prof. Deva Ramanan. Before that, I worked at Video Analytics Lab, Indian Institute of Science, on computer vision problems and at Microsoft, improving search at Bing scale.
I graduated from Indian Institute of Technology Kharagpur majoring in Mathematics and Computing.
I have enjoyed working 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
|
|
Research
I am excited about developing state-of-the-art algorithms and formulating relevant research problems that enablerobots to sense and perceive the world as humans do. Presently, my research is focused on autonomous driving andpoint clouds, unsupervised learning, domain adaptation and transfer learning
Reviewer: CVPR 2022-2024, ICRA 2021, 2023-2024, NeurIPS 2023 DGM4H, NeurIPS 2021 ICBINB, MLRC 2020, 2022.
|
Papers (* joint first authors)
|
|
Lidar Panoptic Segmentation and Tracking without Bells and Whistles
Abhinav Agarwalla*,
Xuhua Huang*,
Jason Ziglar,
Francesco Ferroni,
Laura Leal-Taixé,
James Hays,
Aljoša Ošep,
Deva Ramanan
IROS, 2023
paper /
code
The paper introduces a detection-centric network for lidar panoptic segmentation (LPS) and tracking on 3D Lidar point clouds, challenging the conventional "bottom-up" approach. The network utilizes trajectory-level point supervision to obtain `modal` annotations. These are then utilized to predict fine-grained instance segments across time.
|
|
Completely Self-Supervised Crowd Counting via Distribution Matching
Abhinav Agarwalla*,
Deepak Babu Sam*,
Jimmy Joseph,
Vishwanath A. Sindagi,
R. Venkatesh Babu,
Vishal M. Patel
ECCV, 2022
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.
|
|
Beyond Learning Features: Training a Fully-functional Classi-fier with ZERO Instance-level Labels
Abhinav Agarwalla*,
Deepak Babu Sam*,
R. Venkatesh Babu
AAAI, 2022
ICML 2021 Workshop on Self-Supervised Learning for Reasoning and Perception
poster
Existing unsupervised methods require some annotated samples to facilitate the final task-specific predictions.
Instead, we leverage the distribution of labels for supervisory signal such that no image-label pair is needed for training a classifier.
|
|
Towards Deployable Multi-Domain Learning for Inductive-Transductive Transfer
Abhinav Agarwalla*,
Jogendra Nath Kundu*,
Suvaansh Bhambri,
Varun Jampani,
R. Venkatesh Babu
Technical Report
paper
We propose a universal framework to handle both task and domain shifts, and report state-of-the-art results on single/multi-source domain adaptation and domain generalisation.
|
|
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
paper
We integrate learning and motion planning for soccer playing differential drive robots using Bayesian optimisation.
|
|
Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach
Avisek Lahiri*,
Abhinav Agarwalla*,
Prabir Kumar Biswas
ICVGIP 2018
paper /
code
|
|
Recurrent Memory Addressing for describing videos
Arnav Kumar Jain*,
Abhinav Agarwalla*,
Kumar Krishna Agrawal,
Pabitra Mitra
DeepVision , CVPR 2017
paper
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.
|
|
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.
|
|