Sruthi Sudhakar

I am a first-year PhD student at Columbia University advised by Carl Vondrick and Richard Zemel. My work is supported by the NSF Graduate Research Fellowship. Previously, I completed my B.S. in Computer Science at Georgia Tech where I worked on Algorithmic Fairness advised by Judy Hoffman

I have had the opportunity to intern at Microsoft Research (2022) with Vibhav Vineet. I have spent 3 summers working as a Software Engineering Intern with Bloomberg and Microsoft. I am also an active mobile app development volunteer for YogaSangeeta.

In my free time, I enjoy classical indian dancing, drawing, and spending time with friends and family. Feel free to email me to chat about research, grad school applications, or life!

Email  /  CV

profile photo
Research

I'm interested in developing computer vision and deep learning methods to build represnetations for non-rigid objects (from images) which abide by real-world physical properties (shape, motion, affordances) and allow for human interaction.

ICON2: Reliably Benchmarking Predictive Inequity in Object Detection
Sruthi Sudhakar, Viraj Prabhu, Olga Russakovsky, Judy Hoffman,
CVPR SSAD Workshop, 2023
arXiv

ICON2 leverages prior knowledge on the deficiencies of object detection systems to identify performance discrepancies across sub-populations, compute correlations between these potential confounders and a given sensitive attribute, and control for the most likely confounders to obtain a more reliable estimate of model bias.

Mitigating Bias in Visual Transformers via Targeted Alignment
Sruthi Sudhakar, Aravind Krishnakumar, Viraj Prabhu, Judy Hoffman,
BMVC, 2021
arXiv

TADeT: A targeted alignment strategy for debiasing transformers that aims to discover and remove bias primarily from query matrix features.

UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models
Aravind Krishnakumar, Sruthi Sudhakar, Viraj Prabhu, Judy Hoffman,
BMVC, 2021
arXiv

UDIS identifies subpopulations via hierarchical clustering of dataset embeddings and surfaces systematic failure modes by visualizing low performing clusters along with their gradient-weighted class-activation maps.

Teaching

TA, Representation Learning with Prof. Carl Vondrick, Columbia University

TA, Computer Vision with Prof. Judy Hoffman , Georgia Tech


Website Credit, Jon Barron.