Karan Desai

Karan Desai

Building World Labs from the ground up.

I finished my PhD in Computer Science at the University of Michigan in May 2024, advised by Justin Johnson. I do computer vision, and these days I spend most of my time in building high-quality datasets. My PhD thesis, titled Language Supervision for Computer Vision, is available publicly. In my free time, I love rickrolling all my friends.

Feel free to say hi: kdexd at umich dot edu


Selected Publications

meru
Hyperbolic Image-Text Representations
Karan Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson, Ramakrishna Vedantam
ICML 2023 paper bibtex code
lgssl
Learning Visual Representations via Language-Guided Sampling
Mohamed El Banani, Karan Desai, Justin Johnson
CVPR 2023 paper bibtex code
redcaps
RedCaps: Web-curated image-text data created by the people, for the people
Karan Desai, Gaurav Kaul, Zubin Aysola, Justin Johnson
NeurIPS 2021 (Datasets and Benchmarks) paper bibtex code website
cast
CASTing Your Model: Learning to Localize Improves Self-Supervised Representations
Ramprasaath R. Selvaraju*, Karan Desai*, Justin Johnson, Nikhil Naik
CVPR 2021 paper bibtex code blog
virtex
VirTex: Learning Visual Representations from Textual Annotations
Karan Desai and Justin Johnson
CVPR 2021 paper bibtex code website video
probnmn
Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering
Ramakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach, Dhruv Batra, Devi Parikh
ICML 2019 paper bibtex code website
nocaps
nocaps: novel object captioning at scale
Harsh Agrawal*, Karan Desai*, Yufei Wang, Xinlei Chen, Rishabh Jain, Mark Johnson, Dhruv Batra, Devi Parikh, Stefan Lee, Peter Anderson
ICCV 2019 paper bibtex code website

First Projects

These are my humble beginnings, I try to keep them functional over the years!

digit-classifier
digit-classifier
My first neural network using numpy (2015), a multi layer perceptron classifier for MNIST. Back then, this repo made to the Github trending charts for almost two weeks. Simpler times.
snake
snake
My first github repository (2015), snake game implemented in JavaScript. The game is still functional and hosted on Github pages.