Srishti Yadav

Srishti Yadav

ML Researcher

About Me

I am a graduate from Simon Fraser University, Canada where was a Research Assistant at Networked Robotics and Sensing Laboratory under the supervision of Prof. Shahram Payandeh. My work revolved around intersection of computer vision and machine learning. I worked on problem of semi-supervised detection-based-tracking using kinect based RGB and depth images for a mobile robot.

In past, I also worked 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.

In (long) past, I was 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).

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. 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.

Note: If you are someone who wants to chat about Masters (especially research-track) in Canada, DO-NOT hesitate to email me. I’ll be more than happy to tell you about it!

Interests

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

Education

  • Masters (Research-Track), 2021

    Simon Fraser University, Canada

Recent Posts

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.

KL-Divergence

What is KL-Divergence KL Divergence is a measure of how one probabilty distributon is different from another. Some people also call it the distance between two distributions, however, strictly speaking it is not the distance.

Low/Few Shot Learning

Question: If a class has only two samples, can a computer make correct prediction? Note: Number of samples is too less for training. Approach: Few Shot Learning Few shot learning is a problem where we try to learn when the training data is very small.