Srishti Yadav

Srishti Yadav

Research Assistant

Simon Fraser University, Canada

About Me

I am currently a graduate research assistant at Networked Robotics and Sensing Laboratory under the supervision of Prof. Shahram Payandeh at Simon Fraser University, Canada. My work revolves around intersection of computer vision and machine learning. I am working on problem of semi-supervised tracking using RGB and depth images for a mobile robot. We explore attention-based trackers (deep learning) and correlation filter-based trackers (non-deep learning). Attention-based models provided high accuracy, but offline training is a bottleneck. On the other hand, correlation filter-based trackers provided the ability to learn on the fly at high FPS which suite our purpose, hence form a major part of my research.

In past, I have been a part of Helicopter and VTOL Laboratory, IIT Kanpur (supervised by Prof. Abhishek), Samsung IoT Innovation Lab, IIT Delhi (supervised by Prof. Brejesh Lall) and Applied Cognitive Science Lab, IIT Mandi (supervised by Prof. Varun Dutt).

I was lately an intern at UrtheCast where I was responsible for developing computationally intensive image processing algorithms for large scale satellite data within a cloud-based infrastructure using deep learning.

Over the course of my work experience, I have developed excellent skills in PyTorch, TensorFlow, Python, MATLAB, Numpy, Scipy, OpenCV, Matplotlib, GDAL, etc. scientific stack as well as cloud services like AWS.

I am an active member of developer community groups of Vancouver where I run Women in Machine Learning and Data Science meetup and Google Developers Group. As a strong proponent of tech and diversity, my involvement goes beyond local community work. In past, I have been one of the the chairs of Women in Computer Vision workshop co-hosted with CVPR, 2020 and was on the committe of the Women in Machine Learning workshop, 2019. I am currently an advisor for the Women in Computer Vision workshop, 2021 to be co-hosted with CVPR, 2021.

If you have questions about any of my work, feel free to reach out to me via email. I’ll be happy to chat!

Interests

  • Semi-supervised learning
  • Low shot Learning
  • Class imbalance problems
  • Hyperparameter tuning

Education

  • MASc in Engineering Science, 2020

    Simon Fraser University, Canada

Recent Posts

[Coming Up] Hypernetworks

Paper: PDF: HyperNetworks Blog : Blog on Hypernetworks Fig 1. Photo via David Ha's Blog Coming up soon!

[Coming Up] SimCLR: Contrastive Learning of Visual Representations

Paper PDF: SimCLR: Contrastive Learning of Visual Representations Blog: Advancing Self-Supervised and Semi-Supervised Learning with SimCLR Fig 1. Photo via Google AI's Blog Coming up soon!

CLIP: Connecting Text and Images

Paper: Learning Transferable Visual Models From Natural Language Supervision PDF: Learning Transferable Visual Models From Natural Language Supervision Blog: CLIP: Connecting Text and Images General Terms:

Datasets for Fine-Grained Image Classification

iNat2017 Data: https://github.com/visipedia/inat_comp/tree/master/2017 iNat2018 and iNat2019 Data: https://github.com/visipedia/inat_comp/blob/master/2018/README.md Data: https://github.com/visipedia/inat_comp Details: The dataset is similar to iNat2017 with small differences, which are mentioned in the website.

Hyperopt: A tool for parameter tuning

In deep learning, it is not easy to tune hyperparameters for optimal results. If we have 2 parameters (each with 3 prior desirable values), it is an easier problem. We will have possible combinations to try.