Avatar

Research Assistant

Carnegie Mellon University

Biography

I am Ayush Jain, a final year student pusrsuing B.E. in computer science from BITS Pilani, Pilani Campus. Currently, I am also a research assistant at Carnegie Mellon University advised by Prof. Katerina Fragkiadaki. My research interests include computer vision and its intersection with language and control. I want to enable self-supervised robots that can learn about the world in a never-ending learning fashion without requiring explicit human supervision.

Interests

  • Computer Vision
  • Natural Language Processing
  • Reinforcement Learning

Education

  • B.E. in Computer Science, 2021

    BITS PILANI, Pilani Campus

Featured Publications

Ayush Jain*, Gabriel Sarch*, Zhaoyuan Fang*, Adam Harley, Katerina Fragkiadaki
November 2020 Under Review (CVPR 2021)

Move to See Better: Towards Self-Supervised Amodal Object Detection

Humans learn to better understand the world by moving around their environment to get more informative viewpoints of the scene. Most methods for 2D visual recognition tasks such as object detection and segmentation treat images of the same scene as individual samples and do not exploit object permanence in multiple views. Generalization to novel scenes and views thus requires additional training with lots of human annotations. In this paper, we propose a self-supervised framework to improve an object detector in unseen scenarios by moving an agent around in a 3D environment and aggregating multi-view RGB-D information.

PDF Code Project

News

[Aug 2020] I’ll be attending Google Research India’s AI Summer School (Computer Vision track) from August 20-22, 2020!

[May 2020] Joined Prof. Katerina Fragkiadaki’s Lab as Research Associate at Carnegie Mellon University.

Recent Publications

Move to See Better: Towards Self-Supervised Amodal Object Detection

Humans learn to better understand the world by moving around their environment to get more …
Ayush Jain*, Gabriel Sarch*, Zhaoyuan Fang*, Adam Harley, Katerina Fragkiadaki
Under Review (CVPR 2021).
PDF Code Project

AI-enabled Object Detection in Unmanned Aerial Vehicles for Edge Computing Applications

Unmanned Aerial Vehicles (UAVs) are emerging as a powerful tool for various industrial and smart …
Ayush Jain*, Rohit Ramaprasad*, Pratik Narang, Murari Mandal, Vinay Chamola, F. Richard Yu, Mohsen Guizani
Under Review (IEEE comsoc).
PDF Code Project

VisDrone-DET2020: The Vision Meets Drone Object Detection in Image Challenge Results

The Vision Meets Drone Object Detection in Image Challenge (VisDrone-DET 2020) is the third annual …
Dawei Du, Longyin Wen, Pengfei Zhu, Heng Fan, Qinghua Hu, Haibin Ling, Mubarak Shah, Junwen Pan, Ayush Jain, Pratik Narang, et al.
ECCV 2020 Workshop Paper (In Press).

NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain

Significant advances have been made in recent years on Natural Language Processing with machines …
Ayush Jain*, N.M. Meenachi, B. Venkatraman
PDF Code Project Slides

Experience

 
 
 
 
 

Research Associate

Carnegie Mellon University

May 2020 – Present Pittsburgh, Pennsylvania, USA
Under the supervision of Prof. Katerina Fragkiadaki, I worked on enabling an embodied agent to learn about objects without ground truth supervision in an unseen 3D environment just by moving around. I am currently working on embodied language grounding under weak supervision.
 
 
 
 
 

Research Assistant

BITS PILANI

Aug 2019 – Apr 2020 Rajasthan, India
As a research assistant, I worked under the guidance of Prof. Pratik Narang on Aerial Object Detection. My team and I proposed a novel architectural design that improved the performance of previous methods by a substantial margin.
 
 
 
 
 

Research Assistant

Indira Gandhi Center for Atomic Research

May 2019 – Jul 2019 Tamil Nadu, India
I worked on building and releasing two new Nuclear Domain Textual Datasets, and proposing a data efficient BERT based baseline.

Projects

Towards Learning Spatial Common Sense Through Weak Supervision : A Comparitive Study

Reviewed, compared and analysed three recent papers proposed in generalising to novel views through the use of view-prediction …

ABB Robot Simulation

Built simulation of various tasks like writing a cursive and block alphabets on a paper and building complex curved designs using …

Named Entity Recognition from scratch

Built multilayer perceptron network for Named Entity Recognition on CONLL2003 dataset from scratch, implementing backpropagation and …

Compiler Construction

erplag-cc is a compiler for the custom language ERPLAG, written in C. The compiler generates assembly code that can be run on a Linux …

AI Minesweeper

An artificially agent created to play Minesweepers. external_link.

Earthquake Prediction and Management

Implemented Rundle et al.’s research paper for probabilistic prediction of earthquake based on nowcasting. Using the previous …

Teaching and Mentoring

I have served as a teaching assistant for the following courses at BITS Pilani:

  • CS F407 Artificial Intelligence, Fall 2020
  • CS F464 Machine Learning, Spring 2020
  • CS F111 Computer Programming, Spring 2019 and Fall 2019