Sunnie S. Y. Kim

I'm a first-year CS PhD student at Princeton University working with Olga Russakovsky in the Princeton Visual AI Lab.

Previously, I received a B.S. degree in Statistics and Data Science at Yale University and worked with John Lafferty on generative models and visual information encoding in the Yale Statistical Machine Learning Group. After graduation, I spent a year at Toyota Technological Institute at Chicago doing computer vision and machine learning research with Greg Shakhnarovich.

Email  /  Github  /  Google Scholar  /  Twitter

News

05/2021: Cleaning and Structuring the Label Space of the iMet Collection 2020 has been accepted to the CVPR 2021 FGVC workshop.
03/2021: [Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias has been selected for publication in the ReScience C journal.
03/2021: Led a discussion on the costs and risks of large language models in the Princeton Bias in AI Reading Group (slides).
02/2021: Two papers accepted to CVPR 2021: Fair Attribute Classification through Latent Space De-biasing & Information-Theoretic Segmentation by Inpainting Error Maximization.
01/2021: Participated in the ML Reproducibility Challenge 2020, i.e. reproduced a CVPR 2020 paper in full and wrote a 12 page report (+ 13 page appendix).
11/2020: Gave a short guest lecture on image synthesis in Princeton’s undergraduate computer vision course (slides).
09/2020: Gave a talk on Deformable Style Transfer at Princeton PIXL Talks (slides).
08/2020: Started my PhD at Princeton University!
08/2020: Attended ECCV 2020 and presented Deformable Style Transfer at the main conference and the WiCV workshop.
07/2020: Wrapped up my time at TTIC as a visiting student. The year went by very quickly. I’ll especially miss the Perception and Learning Systems group, the 2019-2020 cohort friends, and the Girls Who Code team!
Research

I’m interested in computer vision and machine learning, especially in building more fair, interpretable, and reliable visual systems. Currently, I'm focusing on developing my research skills and building a background in various areas.

* denotes equal contribution.

Cleaning and Structuring the Label Space of the iMet Collection 2020
Vivien Nguyen*, Sunnie S. Y. Kim*
CVPR 2021 Fine-Grained Visual Categorization Workshop
paper / extended abstract / code / bibtex

Cleaned and structured the noisy label space of the iMet Collection dataset for fine-grained art attribute recognition.

[Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias
Sunnie S. Y. Kim, Sharon Zhang, Nicole Meister, Olga Russakovsky
ReScience C 2021 (ML Reproducibility Challenge 2020)
paper (journal) / paper (arxiv) / code / openreview / bibtex

Reproducibility report on Singh et al. (CVPR 2020) that mitigates contextual bias in object and attribute recognition.

Fair Attribute Classification through Latent Space De-biasing
Vikram V. Ramaswamy, Sunnie S. Y. Kim, Olga Russakovsky
CVPR 2021
project page / paper / code / bibtex

GAN-based data-augmentation method for fairer attribute classification.

Information-Theoretic Segmentation by Inpainting Error Maximization
Pedro Savarese, Sunnie S. Y. Kim, Michael Maire, Greg Shakhnarovich, David McAllester
CVPR 2021
project page / paper

Cheap, class-agnostic, and learning-free method for unsupervised image segmentation.

Deformable Style Transfer
Sunnie S. Y. Kim, Nicholas Kolkin, Jason Salavon, Gregory Shakhnarovich
ECCV 2020
project page / paper / code / demo / 1min video / 10min talk / slides / bibtex

Integration of texture and geometry style transfer.

2018 Environmental Performance Index
Zachary A. Wendling, Daniel C. Esty, John W. Emerson, Marc A. Levy, Alex de Sherbinin, et al.
website / report & data / discussion at WEF18 / news 1 / news 2

A biennial report produced by researchers at Yale and Columbia, in collaboration the World Economic Forum. I built the full data pipeline and led the data programming and analysis work.

Service

Organizing Committee: NESS NextGen Data Science Day 2018

Program Committee (Reviewer): ML Reproducibility Challenge 2020, CVPR 2021 Responsible Computer Vision Workshop

Conference Volunteer: NeurIPS 2019, ICLR 2020, ICML 2020, NeurIPS 2020

Website modified from here.