Divyansh Jha

Brief bio

I am interested in deep learning research in the broadly in 3d computer vision, natural language processing and robotics. I also like to apply these techniques in different domains like Geographical Information Systems (GIS) and healthcare.

I am currently working as a data scientist at Esri R&D Center, New Delhi, where my primary responsibility is to add deep learning capabilities to the ArcGIS API for Python. I have contributed in the learn module of ArcGIS API for Python which helps the users to prepare data, train and deploy deep learning models for various GIS workflows.

I am also working as a research intern at King Abdullah University of Science and Technology (KAUST) with Dr. Mohamed Elhoseiny (Assistant Professor of CS at KAUST & Visiting Faculty at Stanford).

I graduated from Guru Gobind Singh Indraprastha University with a major in Electronics and Communication Engineering in 2019.

Reach me out at: divyanshj.16@gmail.com. Here is my detailed resume

News

• [Sep 2020] Serving as mentor for NeurIPS 2020 Climate Change AI workshop
• [Aug 2020] Attending ECCV (Remote)
• [Feb 2020] Started working as Research Intern at KAUST (Remote)
• [May 2019] Started working at Esri R&D center
• [May 2019] Graduate from GGSIPU, majoring in ECE
• [Mar 2019] Attending Esri Developer Summit in Palm Springs, CA
• [May 2018] Started internship at Geonuma Softwares (later became Esri R&D)

Blogs

• Implementing SPADE using fastai

  I was fascinated by the results of Nvidia's latest research paper when it came out. If you haven't looked at the paper result then you are missing out. Also, have a look at SPADE based GAN in action in the GIF.

• Swimming pool detection and classification using deep learning

  Object detection is one of the most important tasks in the field of Computer Vision. Locating a specific object in an image is a trivial task for humans, but can be quite challenging for machines. The field has recently witnessed groundbreaking research with state of the art results, but taking this research to the field and solving real-world problems is still a challenge.

• Not just another GAN paper - SAGAN

  Today I am going to discuss a recent paper which I read and presented to some of my friends. I found the idea of the paper so simple that I felt it could be understood by anybody with little knowledge of Generative Adversarial Networks like me.