Animesh Gupta

Animesh Gupta

animeshgupta.thapar(at)gmail.com

Biography

I’m a third-year Electronics and Computer Engineering undergraduate student at Thapar University, Patiala, India. My research focus is broadly centered around Computer Vision and Deep Learning. I work on research projects dealing with Generative Adversarial Networks, Knowledge Distillation, and zero-shot classificatiom. I intend to explore deep model under low-resource training data scenario using semi-supervised and self-supervised paradigm.

I have worked as a Research Intern at SketchX and Inception Institute of Artificial Intelligence. I have also worked as a part-time Research Engineer at a startup Minus Zero where I worked on an autonomous electric car with level 5 autonomy.

News

  • [June 2021] Got selected for Weights & Biases Machine Learning Reproducibility Challenge, Spring 2021 Grant.
  • [June 2021] Got selected for Prairie/MIAI Summer School 2021, INRIA.
  • [May 2021] Volunteered for the ICLR Conference 2021.
  • [June 2020] Got selected for Gaussian Process Summer School 2020, Sheffield University.
  • [September 2020] Won Bronze Metal for Kaggle Notebook in I’m Something of a Painter Myself challenge.
  • [July 2020] Top 42% Worldwide in Google Landmark Recognition 2020.

Interests

  • Computer Vision
  • Deep Learning
  • Reinforcement Learning

Education

  • Bachelor's in Electronics and Computer Engineering, 2023

    Thapar University

Experience

 
 
 
 
 

Research Intern

SketchX

Jul 2021 – Dec 2021 Remote

Created a solution for training a model without any dataset with a minimal difference in accuracy of 3%, as compared with a model trained using the dataset.”. Responsibilities include:

  • Reproduced and verified the codebases of the latest Knowledge Distillation papers.
  • Discussing daily findings with the supervisor.
 
 
 
 
 

Research Intern

Inception Institute of Artificial Intelligence

Apr 2021 – Jun 2021 Remote

Worked on reimplementing and verifying the claims made in the ECCV 2020 paper titled “Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification”. Responsibilities include:

  • Conducted different experiments and ported the code to latest PyTorch version.
  • Wrote a techincal report consisting of details about the experiments.
 
 
 
 
 

Research Engineer (Part-time)

Minus Zero

Nov 2020 – Mar 2021 Patiala

Worked on the road segmentation problem for autonomous cars in India. Responsibilities include:

  • Data Pipeline
  • Modelling
 
 
 
 
 

Research Intern

Indian Institute of Information Technology Allahabad

Nov 2020 – Jan 2021 Allahabad

Worked on scene text detection problem with state of the art model. Responsibilities include:

  • Testing various kind of neural networks
  • Modelling

Projects

ZSl Generative

An Open Source Zero Shot classification toolbox based on PyTorch.

I’m Something of a Painter Myself

Developed a GAN that generates 7,000 to 10,000 Monet-style images.

AI for Blind

Developed a classification model for predicting seven emotions like (angry, disgusted,fearful, happy, neutral, sad and surprised) using FER-2013 dataset.

Google Landmark Recognition 2020

Developed a classification model for predicting landmark labels using the GLDv2 dataset.

Open Source Contributions

pyprobml

  • Added new figures in python for the Kevin Murphy’s book “Probabilistic Machine Learning: An Introduction”.

Openstreetmap

  • To make new geo-locations accessible to new mappers added several new presets.

CircuitVerse

  • Added improvements (like modals, dark mode bugs) for enhancing the use of GUI interface.

Face-X

  • Added NasNet and Xception model architecture for the face recognition.

CoinShift-Imaging-Box

  • Added YOLOv5 example for the object detection.

d2l study group

  • Maintainer of the study group with daily discussions with the students of our college on the book Dive into deep learning.

DSC (Thapar University OfficialWebsite)

  • Improved repository readability for new user navigation.

Mini-Conf

  • Virtual conference toolkit. Added video links and issue tracker bots.