Sanghyuk Chun

I'm a research scientist at NAVER Clova AI Research (CLAIR), working on machine learning and its applications. Prior to working at NAVER, I worked as a research engineer at advanced recommendation team (ART) in Kakao from 2016 to 2018.

I received a master's degree in Electrical Engineering from KAIST in 2016. During the master's degree, I researched on a scalable algorithm for robust subspace clustering. Before my master's study, I worked at IUM-SOCIUS in 2012 as a software engineering internship. I also did a research internship at Networked and Distributed Computing System Lab in KAIST and NAVER Labs during summer 2013 and fall 2015, respectively.

My research goal is to understand unexpected and less interpretable behaviors of machine learning (ML) models and to solve the problems in both practical and provable manners. In particular, I believe that it is important to solve four main research topics: (i) Understanding machine learning models by explainable ML, (ii) Building generalizable models to different biases, corruptions, or domains, (iii) Developing probabilistic machines with well-calibrated uncertainty measurement, (iv) Overcoming insufficient labeled data points by learning with minimal human supervision.

2020



1. Data-driven Harmonic Filters for Audio Representation Learning.
   • Minz Won, Sanghyuk Chun, Oriol Nieto, Xavier Serra
   • ICASSP 2020.
   • [bibtex]


2. Evaluating Weakly Supervised Object Localization Methods Right.
   • Junsuk Choe^*, Seong Joon Oh^*, Seongho Lee, Sanghyuk Chun, Zeynep Akata, Hyunjung Shim
   • arXiv 2020.
   • [paper] [code] [bibtex]



2019



3. Neural Approximation of Auto-Regressive Process through Confidence Guided Skimming.
   • YoungJoon Yoo, Sanghyuk Chun, Sangdoo Yun, Jung-Woo Ha, Jaejun Yoo
   • arXiv 2019.
   • [paper] [bibtex]


4. Learning De-biased Representations with Biased Representations.
   • Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, Jaegul Choo, Seong Joon Oh
   • arXiv 2019.
   • [paper] [bibtex]


5. Toward Interpretable Music Tagging with Self-attention.
   • Minz Won, Sanghyuk Chun, Xavier Serra
   • arXiv 2019.
   • [paper] [code] [bibtex]


6. CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features.
   • Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, Youngjoon Yoo
   • ICCV 2019. Oral presentation (200/4303=4.6%)
   • [paper] [code] [official blog post] [bibtex]


7. Photorealistic Style Transfer via Wavelet Transforms.
   • Jaejun Yoo^*, Youngjung Uh^*, Sanghyuk Chun^*, Byungkyu Kang, Jung-Woo Ha
   • ICCV 2019.
   • [paper] [code] [video stylization results] [official blog post] [bibtex]


8. Automatic Music Tagging with Harmonic CNN.
   • Minz Won, Sanghyuk Chun, Oriol Nieto, Xavier Serra
   • ISMIR LBD 2019.
   • [paper] [bibtex]


9. An Empirical Evaluation on Robustness and Uncertainty of Regularization methods.
   • Sanghyuk Chun, Seong Joon Oh, Sangdoo Yun, Dongyoon Han, Junsuk Choe, Youngjoon Yoo
   • ICML Workshop 2019.
   • [paper] [bibtex]


10. Visualizing and Understanding Self-attention based Music Tagging.
    • Minz Won, Sanghyuk Chun, Xavier Serra
    • ICML Workshop 2019. Contributed talk
    • [paper] [code] [talk by Minz] [bibtex]


11. Where To Be Adversarial Perturbations Added? Investigating and Manipulating Pixel Robustness Using Input Gradients.
    • Jisung Hwang^*, Younghoon Kim^*, Sanghyuk Chun^*, Jaejun Yoo, Ji-Hoon Kim, Dongyoon Han
    • ICLR Workshop 2019.
    • [paper] [bibtex]



~ 2018



12. Multi-Domain Processing via Hybrid Denoising Networks for Speech Enhancement.
    • Jang-Hyun Kim^*, Jaejun Yoo^*, Sanghyuk Chun, Adrian Kim, Jung-Woo Ha
    • arXiv 2018.
    • [paper] [project page] [bibtex]


13. A Study on Intelligent Personalized Push Notification with User History.
    • Hyunjong Lee, Youngin Jo, Sanghyuk Chun, Kwangseob Kim
    • Big Data 2017.
    • [paper] [bibtex]


14. Scalable Iterative Algorithm for Robust Subspace Clustering: Convergence and Initialization.
    • Master's Thesis, Korea Advanced Institute of Science and Technology, 2016 (advised by Prof Jinwoo Shin)
    • [paper] [code]

• "Learning generalizable representations with CutMix and REBIS", NAVER Labs Europe (2019).
• "An empirical evaluation on the generalization ability of regularization methods", ICML 2019 Expo Workshop: Recent Work on Machine Learning at NAVER
• "Recent works on deep learning robustness in Clova AI Research", ICLR 2019 Expo Talk: Representation Learning to Rich AI Services in NAVER and LINE
• "Recommendation system in the real world", Deepest Summer School 2018

[카카오AI리포트] 내 손안의 AI 비서, 추천 알고리듬. 전상혁, 김광섭

Participated as an undergraduate researcher for FloSIS: A Highly Scalable Network Flow Capture System for Fast Retrieval and Storage Efficiency (presented at USENIC ATC 2015) (I developed index system described in Section 4.)