Jihoon Tack

I am a Ph.D. student at ALIN-LAB, advised by Prof. Jinwoo Shin at Korea Advanced Institute of Science and Technology (KAIST).

My research focuses on designing algorithms to tackle distributional shifts in machine learning, i.e., training and testing distribution differs. To this end, I focus on developing (i) quick adaptation algorithms for unseen distributions or tasks, and (ii) robust representation learning frameworks. In addition, I have a broad interest in handling complex signals efficiently by utilizing implicit neural representations.

Topics of interest: Meta-Learning, Distributional Shift Robustness, Implicit Neural Representation

(C: Conference, W: Workshop, P: Preprint, *: Equal contribution)

[C9] STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, Jinwoo Shin
International Conference on Learning Representations (ICLR) 2023, Spotlight presentation
NeurIPS Workshop on Table Representation Learning (NeurIPSW-TRL) 2022
paper

[C8] Rethinking the Entropy of Instance in Adversarial Training

Minseon Kim, Jihoon Tack, Jinwoo Shin, Sung Ju Hwang
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) 2023
ICML Workshop on Adversarial Machine Learning (ICMLW-AdvML) 2021
paper

[C7] Meta-Learning with Self-Improving Momentum Target

Jihoon Tack, Jongjin Park, Hankook Lee, Jaeho Lee, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS) 2022
paper | code | slide | poster

[C6] K-centered Patch Sampling for Efficient Video Recognition

Seong Hyeon Park, Jihoon Tack, Byeongho Heo, Jung-Woo Ha, Jinwoo Shin
European Conference on Computer Vision (ECCV) 2022
paper | code

[C5] Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

Sihyun Yu*, Jihoon Tack*, Sangwoo Mo*, Hyunsu Kim, Junho Kim, Jung-Woo Ha,
Jinwoo Shin
International Conference on Learning Representations (ICLR) 2022
CVPR Workshop on AI for Content Creation (CVPRW-AI4CC) 2022
paper | code | slide | project page

[C4] Consistency Regularization for Adversarial Robustness

Jihoon Tack, Sihyun Yu, Jongheon Jeong, Minseon Kim, Sung Ju Hwang, Jinwoo Shin
AAAI Conference on Artificial Intelligence (AAAI) 2022
ICML Workshop on Adversarial Machine Learning (ICMLW-AdvML) 2021, Oral presentation
paper | code | slide | poster

[C3] Meta-Learning Sparse Implicit Neural Representations

Jaeho Lee*, Jihoon Tack*, Namhoon Lee, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS) 2021
Sparsity in Neural Networks Workshop (SNN) 2021
paper | code | slide | poster

[C2] CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Jihoon Tack*, Sangwoo Mo*, Jongheon Jeong, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS) 2020
Qualcomm Innovation Fellowship Korea 2020
paper | code | slide | poster

[C1] Adversarial Self-Supervised Contrastive Learning

Minseon Kim, Jihoon Tack, Sung Ju Hwang
Conference on Neural Information Processing Systems (NeurIPS) 2020
paper | code | project page

[W1] Consistency Regularization for Training Confidence-Calibrated Classifiers

Youngbum Hur*, Jihoon Tack*, Eunho Yang, Sung Ju Hwang, Jinwoo Shin
ICML Workshop on Uncertainty & Robustness in Deep Learning (ICMLW-UDL) 2021
paper

• M.S. & Ph.D. integrated course in Artificial Intelligence, Korea Advanced Institute of Science and Technology (KAIST), 2019 - present (advisor: Prof. Jinwoo Shin)
• B.S. in Electrical Engineering and Mathematics (minored), Korea Advanced Institute of Science and Technology (KAIST), 2014 - 2019

• Top Reviewer Award (top 10%), NeurIPS 2022
• Best Paper Award, Korean Artificial Intelligence Association 2021
• Outstanding Reviewer Award, CVPR 2021
• Winner, Qualcomm Innovation Fellowship Korea 2020
• Top Reviewer Award (top 10%), NeurIPS 2020
• National Science and Engineering Scholarship, Korea Ministry of Science and ICT 2016-2018

• “Consistency Regularization for Adversarial Robustness”
  • @ Korean Artificial Intelligence Association (KAIA), Oral Presentation, Nov 2021
  • @ ICML workshop on AdvML (2021), Contribution Talk, Jul 2021
• “CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances”
  • @ Qualcomm AI Research, Innovation Fellowship Winner Talk, Feb 2021
  • @ NeurIPS Social: ML in Korea, Contribution Talk, Dec 2020
  • @ Korea Software Congress (KSC), Oral Presentation, Dec 2020

• Conference Reviewer
  • NeurIPS 2020, 2021, 2022
  • ICML 2021 (expert), 2022
  • ICLR 2022, 2023
  • CVPR 2021, 2022
  • ICCV 2021
  • AAAI 2023
• Journal Reviewer
  • Transactions on Machine Learning Research
  • IEEE Transactions on Neural Networks and Learning Systems
  • IEEE Transactions on Information Forensics & Security
  • IEEE Transactions on Image Processing

• Confidence-calibrated Regression for Large-scale Used Car Dataset, 2017 - 2020
  Develop an AI system that predicts price, depreciation, and sales duration of used cars.
  Currently, my system is deployed at KBchachacha service (only Korean supported).