Juwon Kang

Researcher, gengenai

Joined

February 2020

Names

Juwon Kang (Preferred)

Emails

****@postech.ac.kr (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

gengenai (gengen.ai)

2024 – Present

PhD student

CSE, POSTECH (postech.ac.kr)

2016 – 2024

Undergrad student

CSE, POSTECH (postech.ac.kr)

2012 – 2016

Advisors, Relations & Conflicts

PhD Advisor

Suha Kwak

2018 – Present

Expertise

Test-Time Adaptation

2023 – Present

Domain generalization

2022 – Present

Domain Adaptation

2018 – Present

Publications

MemBN: Robust Test-Time Adaptation via Batch Norm with Statistics Memory
Juwon Kang, Nayeong Kim, Jungseul Ok, Suha Kwak
- The 18th European Conference on Computer Vision ECCV 2024
- Readers: Everyone
Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization
Nayeong Kim, Juwon Kang, Sungsoo Ahn, Jungseul Ok, Suha Kwak
- ICML 2024 Poster
- Readers: Everyone
Removing Multiple Shortcuts through the Lens of Multi-task Learning
Nayeong Kim, Juwon Kang, Sungsoo Ahn, Jungseul Ok, Suha Kwak
- Submitted to ICLR 2024
- Readers: Everyone
Leveraging Proxy of Training Data for Test-Time Adaptation
Juwon Kang, Nayeong Kim, Donghyeon Kwon, Jungseul Ok, Suha Kwak
- ICML 2023 Poster
- Readers: Everyone
Style Neophile: Constantly Seeking Novel Styles for Domain Generalization
Juwon Kang, Sohyun Lee, Namyup Kim, Suha Kwak
- 2022 (modified: 21 Nov 2022)
- CVPR 2022
- Readers: Everyone
URIE: Universal Image Enhancement for Visual Recognition in the Wild
Taeyoung Son, Juwon Kang, Namyup Kim, Sunghyun Cho, Suha Kwak
- 2020 (modified: 21 Nov 2022)
- ECCV (9) 2020
- Readers: Everyone
Context-Aware Memory Profiling for Speculative Parallelism
Changsu Kim, Juhyun Kim, Juwon Kang, Jae W. Lee, Hanjun Kim
- 2017 (modified: 21 Nov 2022)
- HiPC 2017
- Readers: Everyone

Juwon Kang

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

MemBN: Robust Test-Time Adaptation via Batch Norm with Statistics Memory

Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization

Removing Multiple Shortcuts through the Lens of Multi-task Learning

Leveraging Proxy of Training Data for Test-Time Adaptation

Style Neophile: Constantly Seeking Novel Styles for Domain Generalization

URIE: Universal Image Enhancement for Visual Recognition in the Wild

Context-Aware Memory Profiling for Speculative Parallelism

Co-Authors