Seunghoon Hong

Assistant Professor

School of Computing, KAIST

I am an assistant professor at the School of Computing, KAIST, leading KAIST Vision and Learning Lab. Before joining KAIST, I was a visiting faculty researcher at Google Brain, and a postdoctoral fellow at University of Michigan collaborated with Professor Honglak Lee on topics related to deep learning and its application to computer vision. I received my Ph.D. degree at POSTECH, Korea under the supervision of Professor Bohyung Han.

My research interests include machine learning and computer vision. Particularly, I am interested in scaling up machine learning algorithms for visual perception by minimizing human supervision for training. I am also interested in making such algorithms interpretable to humans, allowing users to more easily understand and get involved in the decision making process in ML systems.


  • seunghoon.hong@kaist.ac.kr

  • Bldg E3-1, Rm 3429, 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141

  • (+82)-42-350-3579


  • PhD in Computer Science and Engineering, 2017

    POSTECH, Korea

  • BS in Computer Science and Engineering, 2011

    POSTECH, Korea


  • [July 2024] Two papers are accepted to ECCV 2024.
  • [Mar 2024] I will serve as a Senior Area Chair in NeurIPS 2024.
  • [Jan 2024] One paper is accepted to ICLR 2024.
  • [Sept 2023] One paper is accepted to NeurIPS 2023.
  • [April 2023] One paper is accepted to ICML 2023.
  • [Mar 2023] We have received Oustanding Paper Award at ICLR 2023. Huge congraturations to Donggyun, Jinwoo, Seongwoong and Chong!
  • [Feb 2023] One paper is accepted to CVPR 2023.
  • [Jan 2023] Donggyun won a Silver Prize from Samsung HumanTech Award. Congraturations!
  • [Jan 2023] One paper is accepted as an oral presentation at ICLR 2023.
  • [Dec 2022] I was selected as an Outstanding Area Chair at ACCV 2022.
  • [Oct 2022] Jinwoo won Qualcomm Innovation Fellowship Korea 2022. Congraturations!
  • [Sept 2022] Two papers are accepted to NeurIPS 2022.

  • Area Chair: I serve as a senior area chair in NeurIPS 2024 and area chair in NeurIPS 2023, AAAI 2024, CVPR 2024, ICLR 2024


  • Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild

    Donggyun Kim, Seongwoong Cho, Semin Kim, Chong Luo, Seunghoon Hong

    ECCV 2024

    [ arXiv ]

  • MetaWeather: Few-Shot Weather-Degraded Image Restoration

    Youngrae Kim, Younggeol Cho, Thanh-Tung Nguyen, Seunghoon Hong, Dongman Lee

    ECCV 2024

    [ Comming soon ]

  • Revisiting Random Walks for Learning on Graphs

    Jinwoo Kim, Olga Zaghen, Ayhan Suleymanzade, Youngmin Ryou, Seunghoon Hong

    GRaM Workshop @ ICML 2024

    [ arXiv ]

  • Learning to Compose: Improving Object Centric Learning by Injecting Compositionality

    Whie Jung, Jaehoon Yoo, Sungjin Ahn, Seunghoon Hong

    ICLR 2024

    [ Paper ]

  • Learning Symmetrization for Equivariance with Orbit Distance Minimization

    Dat Tien Nguyen*, Jinwoo Kim*, Hongseok Yang, Seunghoon Hong

    NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations

    [ arXiv / Code ]

  • 3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation

    Sungjun Cho, Dae-Woong Jeong, Sung Moon Ko, Jinwoo Kim, Sehui Han, Seunghoon Hong, Honglak Lee, Moontae Lee

    arXiv 2023

    [ arXiv ]

  • Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

    Jinwoo Kim, Dat Tien Nguyen, Ayhan Suleymanzade, Hyeokjun An, Seunghoon Hong

    NeurIPS 2023 spotlight presentation

    [ arXiv / Code ]

  • Information-Theoretic State Space Model for Multi-View Reinforcement Learning

    HyeongJoo Hwang, Seokin Seo, Youngsoo Jang, Sungyoon Kim, Geon-Hyeong Kim, Seunghoon Hong, Kee-Eung Kim

    ICML 2023 Oral presentation

    [ Paper ]

  • Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers

    Jaehoon Yoo, Semin Kim, Doyup Lee, Chiheon Kim, Seunghoon Hong

    CVPR 2023

    [ arXiv / Project / Code ]

  • Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching

    Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong

    ICLR 2023 Outstanding Paper Award 🏆

    [ Paper / Code ]

  • Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost

    Sungjun Cho, Seonwoo Min, Jinwoo Kim, Moontae Lee, Honglak Lee, Seunghoon Hong

    NeurIPS 2022

    [ arXiv / Code ]

  • Pure Transformers are Powerful Graph Learners

    Jinwoo Kim, Tien Dat Nguyen, Seonwoo Min, Sungjun Cho,
    Moontae Lee, Honglak Lee, Seunghoon Hong

    NeurIPS 2022

    [ arXiv / Code ]

  • Equivariant Hypergraph Neural Networks

    Jinwoo Kim, Saeyoon Oh, Sungjun Cho, Seunghoon Hong

    ECCV 2022

    [ arXiv / Code ]

  • Diverse Generative Perturbations On Attention Space For Transferable Adversarial Attacks

    Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon

    ICIP 2022 Oral presentation

    [ arXiv / Code ]

  • MetaDTA: Meta-learning-based Drug-Target Binding Affinity Prediction

    Eunjoo Lee, Jiho Yoo, Huisun Lee, Seunghoon Hong

    MLDD workshop @ ICLR 2022

    [ Paper ]

  • Part-based Pseudo Label Refinement for Unsupervised Person Re-identification

    Yoonki Cho, Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon

    CVPR 2022

    [ arXiv / Code ]

  • Multi-Task Neural Processes

    Donggyun Kim, Seongwoong Cho, Wonkwang Lee, Seunghoon Hong

    ICLR 2022

    [ Paper / Code ]

  • Learning Continuous Representation of Audio for Arbitrary Scale Super-Resolution

    Jaechang Kim, Yunjoo Lee, Seunghoon Hong, and Jungseul Ok

    ICASSP 2022

    [ arXiv / Code ]

  • Learning Economic Indicators by Aggregating Multi-level Geospatial Information

    Sungwon Park, Sungwon Han, Donghyun Ahn, Jaeyeon Kim, Jeasurk Yang,
    Susang Lee, Seunghoon Hong, Jihee Kim, Sangyoon Park, Hyunjoo Yang, Meeyoung Cha

    AAAI 2022

    [ arXiv / Code ]

  • Learning to Generate Novel Classes for Deep Metric Learning

    Kyungmoon Lee, Sungyeon Kim, Seunghoon Hong, Suha Kwak

    BMVC 2021

    [ Paper ]

  • Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs

    Jinwoo Kim, Saeyoon Oh, Seunghoon Hong

    NeurIPS 2021

    [ arXiv / Code ]

  • Multi-View Representation Learning via Total Correlation Objective

    HyeongJoo Hwang, Geon-hyeong Kim, Seunghoon Hong, Kee-Eung Kim

    NeurIPS 2021

    [ Paper / Code ]

  • SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data

    Jinwoo Kim*, Jaehoon Yoo*, Juho Lee, Seunghoon Hong

    CVPR 2021

    [ arXiv / Code ]

  • Improving Unsupervised Image Clustering With Robust Learning

    Sungwon Park, Sungwon Han, Sungdong Kim, Danu Kim, Sangkyu Park,
    Seunghoon Hong, Meeyoung Cha

    CVPR 2021

    [ arXiv / Code ]

  • Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction

    Wonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas Huang,
    Hyungsuk Yoon, Honglak Lee, Seunghoon Hong

    ICLR 2021

    [ Paper / Project / Code ]

  • Neural Contrast Enhancement of CT Image

    Minkyo Seo, Dongkeun Kim, Kyungmoon Lee, Seunghoon Hong,
    Jae Seok Bae, Jung Hoon Kim, Suha Kwak

    WACV 2021

    [ Paper ]

  • Variational Interaction Information Maximization for Cross-domain Disentanglement

    HyeongJoo Hwang, Geon-hyeong Kim, Seunghoon Hong, Kee-Eung Kim

    NeurIPS 2020

    [ Paper / Code ]

  • High-Fidelity Synthesis with Disentangled Representation

    Wonkwang Lee, Donggyun Kim, Seunghoon Hong*, Honglak Lee

    ECCV 2020

    [ arXiv / Code ]

  • Residual Neural Processes

    Byung-Jun Lee, Seunghoon Hong, and Kee-Eung Kim

    AAAI 2020

    [ Paper ]

  • Adversarial Defense via Learning to Generate Diverse Attacks.

    Yunseok Jang, Tianchen Zhao, Seunghoon Hong, Honglak Lee

    ICCV 2019

    [ Paper / Code ]

  • Interpretable Text-to-Image Synthesis with Hierarchical Semantic Layout Generation.

    Seunghoon Hong, Dingdong Yang, Jongwook Choi, Honglak Lee

    Bookchapter of "Explainable AI; Interpreting, Explaining and Visualizing Deep Learning" 2019

    [ Paper ]

  • Diversity-Sensitive Conditional Generative Adversarial Networks

    Dingdong Yang*, Seunghoon Hong*, Yunseok Jang, Tiangchen Zhao, Honglak Lee

    ICLR 2019

    [ arXiv / Code / Project ]

  • Learning Hierarchical Semantic Image Manipulation
    through Structured Representations

    Seunghoon Hong, Xinchen Yan, Thomas Huang, Honglak Lee

    NeurIPS 2018

    [ arXiv / Code ]

  • Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis

    Seunghoon Hong, Dingdong Yang, Jongwook Choi, Honglak Lee

    CVPR 2018

    [ arXiv ]

  • Weakly Supervised Learning with Deep Convolutional Neural Networks
    for Semantic Segmentation

    Seunghoon Hong, Suha Kwak, Bohyung Han

    Signal Processing Magazine 2017

    [ Paper ]

  • Weakly Supervised Semantic Segmentation using Web-Crawled Videos

    Seunghoon Hong, Donghun Yeo, Suha Kwak, Honglak Lee, Bohyung Han

    CVPR 2017 Spotlight presentation

    [ arXiv ]

  • Decomposing Motion and Content for Natural Video Sequence Prediction

    Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee

    ICLR 2017

    [ arXiv / Code / Project ]

  • Personalized Image Aesthetic Quality Assessment
    by Joint Regression and Ranking

    Kayoung Park, Seunghoon Hong, Mooyeol Baek, Bohyung Han

    WACV 2017

    [ Paper ]

  • Weakly Supervised Semantic Segmentation
    using Superpixel Pooling Network

    Suha Kwak, Seunghoon Hong, Bohyung Han

    AAAI 2017

    [ Paper ]

  • Learning Transferrable Knowledge for Semantic Segmentation
    with Deep Convolutional Neural Network

    Seunghoon Hong, Junhyuk Oh, Bohyung Han, Honglak Lee

    CVPR 2016 Spotlight presentation

    [ arXiv / Code / Project ]

  • Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation

    Seunghoon Hong*, Hyeonwoo Noh*, Bohyung Han

    NIPS 2015 Spotlight presentation

    [ arXiv / Code / Project ]

  • Learning Deconvolution Network for Semantic Segmentation

    Hyeonwoo Noh, Seunghoon Hong, Bohyung Han

    ICCV 2015

    [ arXiv / Code / Project ]

  • Joint Image Clustering and Labeling by Matrix Factorization

    Seunghoon Hong, Jonghyun Choi, Jan Feyereisl, Bohyung Han, Larry S. Davis

    TPAMI 2015

    [ Paper ]

  • Online Tracking by Learning Discriminative Saliency Map
    with Convolutional Neural Network

    Seunghoon Hong, Tackgeun You, Suha Kwak, Bohyung Han

    ICML 2015

    [ arXiv ]

  • Visual Tracking by Sampling Tree-Structured Graphical Models

    Seunghoon Hong, Bohyung Han

    ECCV 2014 Oral presentation

    [ Paper / Project ]

  • Online Graph-Based Tracking

    Hyeonseob Nam, Seunghoon Hong, Bohyung Han

    ECCV 2014

    [ Paper / Project ]

  • Orderless Tracking through Model-Averaged Posterior Estimation

    Seunghoon Hong, Suha Kwak, Bohyung Han

    ICCV 2013 Oral presentation

    [ Paper / Project ]

  • Joint Segmentation and Pose Tracking of Human in Natural Videos

    Taegyu Lim, Seunghoon Hong, Bohyung Han, Joon Hee Han

    ICCV 2013

    [ Paper ]


Ph.D. Students

MS Students

Undergraduate Students