Kibok Lee

Assistant Professor

Applied Statistics / Statistics and Data Science @ Yonsei University

kibok90 _at_ gmail _dot_ com (for non-academic stuffs)

kibok _at_ yonsei _dot_ ac _dot_ kr

[Google Scholar] [GitHub]

I am an assistant professor at Yonsei University. Previously, I was an applied scientist at Amazon Web Services. I finished my Ph.D. at the University of Michigan, advised by Honglak Lee. My research interests lie in machine learning and computer vision.

New website: https://ml.yonsei.ac.kr/

Research Topics

  • (Self-Supervised) Representation Learning

  • Out-of-Distribution Detection

  • Continual Learning

  • Few-Shot Learning


Publications (C: conference, J: journal, P: preprint, *: equal contribution)

[C13] Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark

Kibok Lee, Hao Yang, Satyaki Chakraborty, Zhaowei Cai, Gurumurthy Swaminathan, Avinash Ravichandran, Onkar Dabeer

In ECCV, 2022. [paper, arXiv:2207.11169][GitHub]

[C12] Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Hankook Lee, Kibok Lee, Kimin Lee, Honglak Lee, Jinwoo Shin

In NeurIPS, 2021. [paper, arXiv:2111.09613][GitHub]

[C11] i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning

Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, Honglak Lee

In ICLR, 2021. [paper, arXiv:2010.08887][GitHub][poster]

[P1] ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds

Kibok Lee, Zhuoyuan Chen, Xinchen Yan, Raquel Urtasun, Ersin Yumer

Preprint. [arXiv:2005.11626]

[C10] Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning

Kimin Lee*, Kibok Lee*, Jinwoo Shin, Honglak Lee

In ICLR, 2020. [paper, arXiv:1910.05396][GitHub]

Preliminary version [poster] was presented in NeurIPS Workshop on Deep Reinforcement Learning, 2019. Contributed talk

[C9] Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild

Kibok Lee, Kimin Lee, Jinwoo Shin, Honglak Lee

In ICCV, 2019. [paper, arXiv:1903.12648][GitHub][poster]

[Short version][slides] was presented in CVPR Workshop on Uncertainty and Robustness in Deep Visual Learning, 2019. Spotlight

[C8] Robust Inference via Generative Classifiers for Handling Noisy Labels

Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li, Jinwoo Shin

In ICML, 2019. Long presentation [paper, arXiv:1901.11300][GitHub]

[C7] Automatic Correction of Lithography Hotspots with a Deep Generative Model

Woojoo Sim*, Kibok Lee*, Dingdong Yang, Jaeseung Jeong, Ji-Suk Hong, Sooryong Lee, Honglak Lee

In SPIE Advanced Lithography, 2019. Invited (long presentation) [paper]

[C6] A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Kimin Lee, Kibok Lee, Honglak Lee, Jinwoo Shin

In NeurIPS, 2018. Spotlight (168/4856=3.5%) [paper, arXiv:1807.03888][GitHub]

Comment: Adversarial samples can be used to validate our proposed method without OOD samples; check the right side of the Table 2.

[C5] Hierarchical Novelty Detection for Visual Object Recognition

Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin, Honglak Lee

In CVPR, 2018. [paper, arXiv:1804.00722][GitHub][poster]

Comment: Hierarchical novelty detection is a generalization of generalized zero-shot learning, in the sense that it does not require semantic information about zero-shot classes.

[C4] Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples

Kimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin

In ICLR, 2018. [paper, arXiv:1711.09325][GitHub]

[C3] Towards Understanding the Invertibility of Convolutional Neural Networks

Anna Gilbert, Yi Zhang, Kibok Lee, Yuting Zhang, Honglak Lee

In IJCAI, 2017. [paper, arXiv:1705.08664][slides][poster]

[C2] Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification

Yuting Zhang, Kibok Lee, Honglak Lee

In ICML, 2016. [paper, arXiv:1606.06582][GitHub][slides][poster]

[J1] A Flexible Framework for Online Document Segmentation by Pair-wise Stroke Distance Learning

Adrien Delaye, Kibok Lee

Pattern Recognition, 2015. [paper (ScienceDirect) (ResearchGate)]

[C1] On the Equivalence of Linear Discriminant Analysis and Least Squares

Kibok Lee, Junmo Kim

In AAAI, 2015. [paper (gdrive)] [supplementary]


Employment

  • 2022-Present: Assistant Professor, Applied Statistics / Statistics and Data Science at Yonsei University, Seoul, Korea

  • 2020-2022: Applied Scientist, Amazon Web Services, WA, US

  • 2019-2019: Research Intern, Uber Advanced Technologies Group, CA, US

  • 2012-2015: Research Engineer, Samsung Electronics, Suwon, Korea


Education

  • Ph.D. in Computer Science and Engineering, University of Michigan, 2020

  • M.S. in Electrical Engineering, KAIST, 2012

  • B.S. in Electrical Engineering, KAIST, 2011


Professional Service

Journal Reviewer

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

  • Journal of Machine Learning Research (JMLR)

  • Transactions on Machine Learning Research (TMLR)

  • International Journal of Computer Vision (IJCV)

Conference Reviewer

  • AAAI 2020-2022

  • ACCV 2020-2022

  • CVPR 2020-2022

  • ECCV 2020-2022

  • ICCV 2019-2021

  • ICLR 2020–2022

  • ICML 2020–2022

  • NeurIPS 2019–2022

  • WACV 2021–2023

Workshop Program Committee

  • ECCV 2022 Workshop on a Challenge for Out-of-Distribution Generalization in Computer Vision

  • ECCV 2022 Workshop on Adversarial Robustness in the Real World

  • NeurIPS 2021 Workshop on Distribution Shifts

  • ICCV 2021 Workshop on Adversarial Robustness In the Real World

  • ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning

  • ECCV 2020 Workshop on Adversarial Robustness in the Real World

  • ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning

  • NeurIPS 2018 Workshop on Continual Learning