Byeonghu Na

2019.02.25 16:59

나병후 Views:2085

나병후a-0104.jpg

 

Byeonghu Na

 

Ph.D. Candidate

Applied Artificial Intelligence Laboratory

Department of Industrial and Systems Engineering

KAIST, Daejeon, Republic of Korea

Contact: wp03052 [at] kaist.ac.kr / byeonghu.na [at] kaist.ac.kr / gwp03052 [at] gmail.com

Homepage: byeonghu-na.github.io

 

RESEARCH INTEREST

  • Machine learning
    • Deep Generative Model: VAE, Diffusion Model, Normalizing Flow
    • Robust Learning: Learning with Noisy Labels, Open-Set Problem, Out-of-Distribution Detection Problem, Spurious Bias Problem
    • Positive-Unlabeled Learning (Special Case of Semi-Supervised Learning)
    • Scene Text Recognition (OCR)

 

EDUCATION

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2021 ~ )

  • Course of Doctor's Degree in AAILab, ISysE
  • Academic Advisor: Professor Il-Chul Moon

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Feb. 2019 ~ Feb. 2021)

  • Course of Master's Degree in AAILab, ISysE
  • Academic Advisor: Professor Il-Chul Moon

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2014 ~ Feb. 2019)​

  • Bachelor of Science in Mathematical Sciences 
  • Bachelor of Science in Industrial and Systems Engineering

 

PUBLICATIONS

International Conference

  • Byeonghu Na, Hyemi Kim, Kyungwoo Song, Weonyoung Joo, Yoon-Yeong Kim, and Il-Chul Moon. 2020. Deep Generative Positive-Unlabeled Learning under Selection Bias. In The 29th ACM International Conference on Information and Knowledge Management (CIKM ’20), October 19–23, 2020, Virtual Event, Ireland. [paper] [code]
  • HeeSun Bae*, Seungjae Shin*, Byeonghu Na, JoonHo Jang, Kyungwoo Song, and Il-Chul Moon. 2022. From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model. In The 39th International Conference on Machine Learning (ICML 2022), July 17-23, 2022, Baltimore, Maryland, USA[paper] [code]
  • Seungjae Shin, Byeonghu Na, HeeSun Bae, JoonHo Jang, Hyemi Kim, Kyungwoo Song, Youngjae Cho, and Il-Chul Moon. 2022. Improving Group-based Robustness and Calibration via Ordered Risk and Confidence Regularization. In The Workshop on Spurious Correlations, Invariance, and Stability, International Conference on Machine Learning (SCIS at ICML 2022), July 22, 2022, Baltimore, Maryland, USA. [paper]
  • Byeonghu Na, Yoonsik Kim, and Sungrae Park. 2022. Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features. In European Conference on Computer Vision (ECCV 2022), October 23-27, 2022, Tel-Aviv, Israel[paper] [code]
  • JoonHo Jang, Byeonghu Na, DongHyeok Shin, Mingi Ji, Kyungwoo Song, and Il-Chull Moon. 2022. Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation. In The Conference on Neural Information Processing Systems (NeurIPS 2022), Nov 28-Dec 9, 2022, New Orleans, USA. [paper]
  • Dongjoun Kim*, Byeonghu Na*, Se Jung Kwon, Dongsoo Lee, Wanmo Kang, and Il-Chul Moon. 2022. Maximum Likelihood Training of Implicit Nonlinear Diffusion ModelsIn The Conference on Neural Information Processing Systems (NeurIPS 2022), Nov 28-Dec 9, 2022, New Orleans, USA. [paper[code]

 

Domestic Conference

  • 신승재, 나병후, 신동혁, 나영연, 문일철 (2017. 12) 인공 신경망 기반 뉴스기사의 토픽 분석 및 문서 분류 동시 수행 모델 개발, 한국정보과학회 [paper]

 

 

AWARDS & SCHOLARSHIPS

  • 관정 국내대학원 장학생, 관정이종환장학재단, 2021 - 2022.
  • SIGIR Student Travel Grant, SIGIR, 2020.
  • 김영한 글로벌리더 장학생, KAIST, 2020.
  • Summa Cum Laude, KAIST, 2019.
  • 학부생부문 최우수상, KSC2017 학부생 논문경진대회, 2017.
  • 이공계 국가우수장학금, 한국장학재단, 2014 - 2017.
  • 고교 상상 장학생, KT&G 장학재단, 2012 - 2013.

 

LAB 

Byeonghu Na is a member of Applied Artificial Intelligence Laboratory. (2019.03 ~)

No. Subject Author Date Views
13 Lee, GeunHo file SESLAB 2011.09.05 6858
12 JoonHo Jang file 장준호 2017.03.01 3277
11 Dongjun Kim file 김동준 2017.08.24 13436
» Byeonghu Na file 나병후 2019.02.25 2085
9 Seungjae Shin file 신승재 2020.03.12 2219
8 HeeSun Bae file 배희선 2020.03.16 1766
7 DongHyeok Shin file 신동혁 2020.03.16 1442
6 Yunkyeong Seo file 서윤경 2020.03.16 2093
5 Suhyeon Jo file 조수현 2021.02.23 1559
4 Muhyun Byun file 변무현 2021.02.26 829
3 Hyungho Na file 나형호 2021.02.28 825
2 Hyeonmin Lee file 이현민 2021.03.01 879
1 Changseok Han file ChangseokHan 2022.02.23 416