Viraj Prabhu

I am a final year CS Ph.D. student at Georgia Tech, advised by Judy Hoffman. I'm interested in making deep visual models generalize across the infinite visual variation in the world: across viewpoints, time, space, and curation. My research has focused on improving such generalization at different stages of the ML lifecycle: proactive strategies that leverage simulation to augment the long-tail of real training data, as well as reactive strategies based on active learning and domain adaptation to recover from unforeseen spatio-temporal distribution shifts. Of late, I have focused on stress-testing visual models for deployment by leveraging foundation models for text and image synthesis to generate language-guided counterfactual images. My research has spanned diverse applications ranging from autonomous driving to medical diagnosis and algorithmic fairness.

I earned my Master's in CS (awarded the MS Research award) in 2019 at Georgia Tech, where I was advised by Devi Parikh and worked on developing visual conversational agents. In grad school, I've had the opportunity to intern at NVIDIA (with Sanja Fidler), Salesforce (with Nikhil Naik), and Curai (with Anitha Kannan). Before that, I've had stints as a research assistant at Virginia Tech (with Dhruv Batra) and Adobe, and as a mentor for Google Summer of Code. I received my Bachelor's degree in Computer Science from BITS Pilani in 2015. In my free time, I enjoy reading, running, soccer, and playing the guitar.

I'm on the job market for industry positions starting Jan 2024! Please reach out (virajp at gatech dot edu) if you think I might be a good fit for your team.

Summer '14, 2015-2016
Summer 2018, 2019
Summer 2021
Summer 2022


Read More

Read Less


LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images

NeurIPS 2023

Viraj Prabhu, Sriram Yenamandra, Prithvijit Chattopadhyay, Judy Hoffman

PaperProject PageNews

Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting

TMLR 2023

Viraj Prabhu, David Acuna, Yuan-Hong Liao, Rafid Mahmood, Marc T. Law, Judy Hoffman, Sanja Fidler, James Lucas


Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Vision Tasks

NeurIPS 2023 (Datasets & Benchmarks)

Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu, Viraj Prabhu, Gowthami Somepalli, Prithivijit Chattopadhyay, Adrien Bardes, Mark Ibrahim, Judy Hoffman, Rama Chellappa, Andrew Gordon Wilson, Tom Goldstein

Translating Labels to Solve Annotation Mismatches Across Object Detection Datasets

Yuan-Hong Liao, David Acuna, Rafid Mahmood, James Lucas, Viraj Prabhu, Sanja Fidler

AUGCAL: Sim-to-Real Adaptation by Improving Uncertainty Calibration on Augmented Synthetic Images

Uncertainty Quantification for Computer Vision, ICCV 2023

Prithvijit Chattopadhyay, Bharat Goyal, Bogi Ecsedi, Viraj Prabhu, Judy Hoffman

FACTS: First Amplify Correlations and Then Slice to Discover Bias

ICCV 2023

Sriram Yenamandra, Pratik Ramesh, Viraj Prabhu, Judy Hoffman

ICON2: Reliably Benchmarking Inequity in Detection by Identifying and Controlling for Confounders

Safe and Secure Autonomous Driving, CVPR 2023

Sruthi Sudhakar, Viraj Prabhu, Olga Russakovsky, Judy Hoffman


Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency

NeurIPS 2022

Viraj Prabhu*, Sriram Yenamandra*, Aaditya Singh, Judy Hoffman (* = equal contribution)


Can domain adaptation make object recognition work for everyone?

Learning with Limited Labelled Data, CVPR 2022

Viraj Prabhu, Ramprasaath R. Selvaraju, Judy Hoffman, Nikhil Naik


AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Segmentation

Computer Vision in the Wild, ECCV 2022 (spotlight)

Viraj Prabhu*, Shivam Khare*, Deeksha Kartik, Judy Hoffman (* = equal contribution)


UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models

BMVC 2021

Arvind Krishnakumar, Viraj Prabhu, Sruthi Sudhakar, Judy Hoffman


Mitigating Bias in Visual Transformers via Targeted Alignment

BMVC 2021

Sruthi Sudhakar, Viraj Prabhu, Arvind Krishnakumar, Judy Hoffman


Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

ICCV 2021

Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

PaperProject PageCodeVideoSlidesPoster

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

ICCV 2021

Viraj Prabhu, Arjun Chandrasekaran, Kate Saenko, Judy Hoffman

PaperProject PageCodeVideoSlidesPoster

Open Set Medical Diagnosis

Machine Learning for Health, NeurIPS 2019

Viraj Prabhu, Anitha Kannan, Geoffrey J. Tso, Namit Katariya, Manish Chablani, David Sontag, Xavier Amatriain


Few-shot Learning for Dermatological Disease Diagnosis

MLHC 2019 (spotlight), Machine Learning for Health, NeurIPS 2018

Viraj Prabhu, Anitha Kannan, Murali Ravuri, Manish Chablani, David Sontag, Xavier Amatriain


Do Explanations make VQA Models more Predictable to a Human?

EMNLP 2018, Chalearn Looking at People, CVPR 2017

Arjun Chandrasekaran*, Viraj Prabhu*, Deshraj Yadav*, Prithvijit Chattopadhyay*, Devi Parikh (* = equal contribution)


The Promise of Premise: Harnessing Question Premises in Visual Question Answering

EMNLP 2017

Aroma Mahendru*, Viraj Prabhu*, Akrit Mohapatra*, Dhruv Batra, Stefan Lee (* = equal contribution)


Evaluating Visual Conversational Agents via Cooperative Human-AI Games

HCOMP 2017

Prithvijit Chattopadhyay*, Deshraj Yadav*, Viraj Prabhu, Arjun Chandrasekaran, Abhishek Das, Stefan Lee, Dhruv Batra, Devi Parikh (* = equal contribution)



Fabrik: An Online Collaborative Neural Network Editor

Utsav Garg, Viraj Prabhu, Deshraj Yadav, Ram Ramrakhya, Harsh Agrawal, Dhruv Batra

Lead mentor on Fabrik, an open-source web platform to collaboratively build, visualize, and design neural networks in the browser.

Report Code

PyTorch implementation of Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning

Nirbhay Modhe, Viraj Prabhu, Michael Cogswell, Satwik Kottur, Abhishek Das, Stefan Lee, Devi Parikh, Dhruv Batra


Adobe Captivate Prime

During my time as a software developer at Adobe (Aug '15-'16), I was responsible for the Captivate Prime Android app through two release cycles. I developed features for offline content play-back, syncing, and UI.

Automated camera calibration

Over a research internship at Tonbo Imaging (Spring '15), I designed and implemented an algorithm for automated camera calibration.


Developed KeyframeCut, a fast graphcut-based segmentation algorithm for real-time background substitution in video, which was tech-transferred to Adobe Presenter Video Express 11.

Demo Blog