Seulki Park

Seulki Park, Ph. D.

I'm a postdoctoral research fellow in Computer Science and Engineering at University of Michigan advised by Prof. Stella X. Yu. I received MS in computer science and PhD degree in electrical and computer engineering at Seoul National University in August, 2019 and 2023, respectively, under the supervision of Prof. Jin Young Choi. I received BA in Applied Statistics from Yonsei University in 2014.

Research Interests

I am interested in solving various problems that arise when applying deep learning algorithms to real-world data. This motivates me to study long-tailed classification, learning from noisy labels/missing attributes, continual learning and robustness of vision-language models. Recently, I'm interested in hierarchical learning and vision-language models.

Work Experience

Publications

Novel Regularization via Logit Weight Repulsion for Long-Tailed Classification 

Taegil Ha, Seulki Park, Jin Young Choi

The British Machine Vision Conference (BMVC), 2023 

RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models 

Seulki Park, Daeho Um, Hajung Yoon, Sanghyuk Chun, Sangdoo Yun, Jin Young Choi

arXiv, 2023 

Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels 

Seulki Park, Hwanjun Song, Daeho Um, Dae Ung Jo, Sangdoo Yun, Jin Young Choi

arXiv, 2023

Confidence-Based Feature Imputation for Graphs with Partially Known Features 

Daeho Um, Jiwoong Park, Seulki Park, Jin young Choi

International Conference on Learning Representations (ICLR), 2023 

Online Boundary-Free Continual Learning by Scheduled Data Prior 

Hyunseo Koh, Minhyuk Seo, Jihwan Bang, Hwanjun Song, Deokki Hong, Seulki Park, Jung-Woo Ha, Jonghyun Choi

International Conference on Learning Representations (ICLR), 2023 

The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification 

Seulki Park, Youngkyu Hong, Byeongho Heo, Sangdoo Yun, Jin Young Choi

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 

Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries 

Jihwan Bang, Hyunseo Koh, Seulki Park, Hwanjun Song, Jung-Woo Ha, Jonghyun Choi

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 

Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning 

Jongin Lim, Sangdoo Yun, Seulki Park, Jin Young Choi

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 

Influence-Balanced Loss for Imbalanced Visual Classification 

Seulki Park, Jongin Lim, Younghan Jeon, Jin Young Choi

IEEE International Conference on Computer Vision (ICCV), 2021