About me

Currently, I am a Ph.D student at Virginia Tech, advised by Devi Parikh.

My current interest includes developing algorithms for Interpreting Deep Neural Networks.

I received my Bachelor of Engineering in Electrical and Electronics, and Master of Science in Physics degrees from BITS-Pilani Hyderabad during the year 2015.

In the past I have held visiting positions at:

  • Virginia Tech, Spring 2015, Research Intern with Devi Parikh
  • Oxford University, Fall 2014, Research Scholar with Philip Torr
  • Brown University, Summer 2013, Research Intern with Benjamin Kimia


  • Aug 2015 - Today

    Ph.D Student advised by Devi Parikh

  • Jan 2015 - July 2015

    Research Intern working with Devi Parikh

  • May 2014 - Dec 2014

    Research Scholar working with Philip Torr

  • May 2013 - Aug 2013

    Summer Intern working with Benjamin Kimia

  • Aug 2010 - May 2014

    Bachelors in Electrical and Electronics Engineering and Master of Science in Physics

My Research

My research interests lie at the intersection of Computer Vision and Machine Learning, with a focus on building algorithms that can:

  • explain why they believe what they believe
  • truly understand and grasp information from different modalities (vision, language, common sense reasoning) and create other plausible scenarios


Grad-CAM: Gradient-weighted Class Activation Mapping
Ramprasaath R. Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh Dhruv Batra
Arxiv Paper: https://arxiv.org/abs/1610.02391 [Code] [Live Demo]

Diverse Beam Search: Diverse Decoding from Neural Sequence Models
Ashwin Kalyan, Michael Cogswell, Ramprasaath R. Selvaraju, Qing Sun, Stefen Lee, David Crandal, Dhruv Batra
Arxiv Paper: Coming soon

Counting Everyday Objects in Everyday Scenes
Prithviraj Chattopadhyay, Ramakrishna Vedantam, Ramprasaath R. Selvaraju, Dhruv Batra, Devi Parikh
[ ArXiv paper]

The Semantic Paintbrush: Interactive 3D Mapping and Recognition in Large Outdoor Spaces
Ondrej Miksik, Vibhav Vineet, Morten Lidegaard, Ramprasaath R. Selvaraju, Matthias Nießner, Stuart Golodetz, Stephen L. Hicks, Patrick Pérez, Shahram Izadi, Philip H. S. Torr [ Paper]
BlindFind: Wearable Computer-Vision Rig for the Visually Impaired
Eduardo Schmidt, Ramprasaath R Selvaraju, Joshua, Brandon, Krishna, Brian, Fırat Kalaycılar, Benjamin Kimia

Latest Blog Post

21 Jan 2017 . . Yes, Deep Networks are great, but are they Trustworthy? Comments

Introduction Need for Transparent Interpretable Systems Conventional approaches to Interpretability
Backpropagation Deconv and Guided Backprop Class Activation Mapping

Grad-CAM- Gradient-weighted Class Activation Mapping
Guided Grad-CAM

Demo Going beyond classification Image-Captioning
Time to try our Grad-CAM Captioning Demo

Visual Question Answering
Time to try our Grad-CAM VQA Demo

Negative Explanations with Grad-CAM Conclusions Acknowledgements


Convolutional Neural Networks (CNNs) and other deep networks have enabled unprecedented breakthroughs in a variety of Computer Vision tasks, ranging from Image Classification (classify the image into a category from a given set of...

View more posts


Please find my resume at this link


Drop me an email if you would like to know any more details about me or my projects

ram21 at vt dot edu