Atharva Chandak personal website describing his experiences, roles, education universities, blog, github codes and others!

Hi! I'm Atharva Chandak

My research interests include

I am a final year Computer Science undergrad student at Birla Institute of Technology and Science, Pilani (BITS Pilani), India.

I've by worked on Deep Learning based Computer Vision and Multi-modal Learning on wide range of research and industrial projects including Action Recognition, Generalized Continual Zero-Shot Learning, Multimodal Advertisement Understanding, etc.

Currently I'm an Intern at Mila / Robotics Group @ University of Montreal working on the Continual Domain-incremental Object Detection.

I like building tools, tech and other hacky things so feel free to connect to discuss any interesting ideas or opportunities!


(Research Intern)
January 2023 - Present
  • Working on continual object detection for autonomous driving.
August 2022 - December 2022
  • Worked on long-range detection and tracking of aerial vehicles to autonomously avoid collisions.
  • Analysed a new dataset for allowing building better models robust to out of distribution climatic conditions.
  • Designed optimized models for real-time usage on the drone capturing high resolution feed from multiple cameras.
May 2022 - July 2022
  • Conceptualized and created an end-to-end AI enabled speech chatbot for answering user home lending queries.
  • Integrated speech-to-text and text-to-speech APIs for allowing speech interaction with the bot.
  • Implemented NLP pipeline for intent and entity extraction and achieved an F1 scores of 93.4% and 83.5% respectively.
  • Authored the action server to process the user request demands and response curation for replying back to user.
(Visiting Research Intern)
January 2022 - May 2022
  • Contributed to the Pytorch Connectomics package adding cellpose model for neuron instance segmentation.
  • Explored semi-supervised methods to improve upon the performance of 3D segmentation.
  • Designed an end-to-end pipeline using long range affinity learning and transformers for improving model accuracy.
(Research Assistant)
April 2021 - Present
  • Investigating various Vision-Transformer networks for fine-grain human action recognition.
  • Reviewed the existing works on fine-grained action recognition and summarised the major research gaps.
  • Exploring better temporal modelling techniques for improving performance on RGB frames directly instead of using optical flow.
(Research Intern)
June 2021 - December 2021
  • Worked on Generalized Continual Zero Shot Learning for various Computer Vision tasks.
  • Integrated the incremental learning setup with zero shot learning for more realistic adaption of DL methods in everyday scenario.
  • Extended the work to generalized, out of distribution tasks and also enable task free learning.
(Research Intern)
May 2021 - August 2021
  • Worked on texture classification of images using both traditional Computer vision with ML algorithms and Deep Learning based methods.
  • Used traditional computer vision algorithms like FAST, ORB & BRISK combined with ML classifiers like SVMs, KNNs, etc.
  • Extended the project to also implement simple image segmentation networks for performing texture segmentation useful for detecting cracks and faults in leather.


music streaming app
# Deep Learning
# Computer Vision
Image Super Resolution with Deep Learning

A GAN based model to convert low resolution images to high resolution.

    Tools: Pytorch
  • Read and implemented various Deep Learning algorithms for image super resolution
  • Used both - GAN based (SRGAN & ESRGAN) and non-GAN based(EDSR and RCAN) approaches .
Screenshot of  web app
# Robotics
# Computer Vision
UAV for parcel delivery

A simulated drone which delivers multiple packages to their destinations, optimizing for time and quantity.

    Tools: Robot Operating System (ROS), Gazebo simulator, OpenCV
  • Control systems (PID building).
  • Path planning & obstacle avoidance.
  • Image processing for marker detection & QR code scanning.
  • Scheduling of the parcels to be delivered and returned.
quiz app
# Web Development
Orca - template website

A jekyll template for easy creation of course websites.

    Tools: HTML, CSS, Bootstrap, Jekyll
  • Created template for easily building a website for any course without having to code the messy HTML & CSS parts.
  • Used jekyll for allowing website to read & display data from .yaml files which can be easily filled by the user.




Libraries & Frameworks



Let's grab a coffee? Or discuss an exciting idea?

Get in touch:
Webite made from template: