Animesh Guptaअनिमेष गुप्ता

I am currently working as Machine Learning Engineer Intern at MVisionAI. I have completed my Bachelors in Electronics and Computer Science from Thapar University, India. Previously, I worked as a Research Intern at UiT, Norway, here I worked on project related to Coreset Subset Selection domain. I have also worked as a research intern at SketchX lab, Unviersity of Surrey, London. At SketchX, I worked on research project dealing with Sketch Visual Understanding. I also worked on industrial projects which try to solve Lane Detection, and Road Segmentation for autonomous cars.

Email  /  Google Scholar  /  Twitter  /  Github  /  Resume/CV

profile photo
What's New
[May 2023] Our paper Big-Bench is accepted at TMLR 2023.
[Feb 2023] Started interning at MVision AI
[July 2022] Adaptive Fine-Grained Sketch-Based Image Retrieval is accpeted in the ECCV 2022.
[May 2022] Joined as Research Intern at UiT - The Arctic University of Norway.
[Mar 2022] Joined as Research Intern at NVIDIA, India
[July 2021] Joined as Research Intern at SketchX, London
[June 2021] Recieved Grant by Weights & Biases for ML Reproducibility Challenge, Spring 2021.
[Oct 2020] Joined as Part-time Research Engineer at Minus Zero
[Feb 2021] Serving as a reviewer for ML Reproducibility Challenge 2020.

Research

I'm interested in developing methods which can effectively train neural networks with limited data. I'm also interested in developing models which can work Multi-Modalities setting like text and sketch.

Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective
Animesh Gupta, Irtiza Hassan, Dilip K Prasad, Deepak K Gupta,
In Submission WACV 2024
Abstract / Code / Paper / BibTex

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench authors
TMLR 2023
Abstract / Code / Paper / BibTex

Adaptive Fine-Grained Sketch-Based Image Retrieval
Ayan Kumar Bhunia, Aneeshan Sain, Parth Hiren Shah,
Animesh Gupta, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song
ECCV 2022
Abstract / Code / Paper / BibTex

Research Experience
Machine Learning Engineer Intern, MVisionAI
February, 2023 - present
Supervisors: Dr. Saad Ullah Akram

  • Working on easing treatment plan for radiotherapy using Image Registration. Radiotherapy involves multiple imaging modalities, e.g. full-field-of-view Computed Tomography (CT) scans is used for planning and Magnetic Resonance Imaging (MRI) scans is used for tumour segmentation.
  • Created an efficient library to facilitate multiple datasets and state-of-the-art algorithms.
  • Adapted RWCNet and Transmorph codebases to reproduce the results of the OASIS and NLST datasets. Formed baseline for the AbdomenCTCT and NLST datasets.

Research Intern, University of Tromso
May 2022 - November 2022
Supervisors: Dr. Deepak Gupta, Dr. Irtiza Hasan, and Dr. Dilip Prasad

  • Created a systematic benchmarking setup for different coreset methods on multiple CNNs and Transformers.
  • Demonstrated that the conventional concept of uniform subset sampling across the various classes of the data is not the appropriate choice
  • The findings of the internship led to a research publication, currently under review at a Machine Learning Journal.

Research Intern, NVIDIA
March 2022 - May 2022

Experimented with latest Real-Time Lane Detection work and vision transformers for an improved solution for DRIVE-Perceptron platform with faster inference and performance.

Research Intern, SketchX
July 2021 - March 2022
Supervisor: Dr. Yi-Zhe Song

  • Worked on Fine-Grained Sketch Based Image Retrieval and Category-Level Sketch Based Image Retrieval.
  • Contributed to the paper which created an adaptive Fine-Grained Sketch-Based Image Retrieval model. It adapts to new categories or different sketching patterns at test time, published in ECCV 2022

Intern, GirlScript Summer of Code
March 2021 - June 2021

  • Face-X: Added NasNet and Xception model architecture for Face Recognition. [PRs]
  • Comet.Box: Added YOLOv5 example for the object detection. [PRs]

Research Engineer, Minus Zero
October 2020 - March 2021

  • Worked on the Road Segmentation problem for autonomous cars in India.
  • Used FCHarDNet as base architecture and trained on the Indian driving dataset (10k images and 34 classes).


I borrowed this website layout from here!