I am a Ph.D candidate at Korea Advanced Institute of Science and Technology (KAIST) advised by Professor Jaegul Choo.

My research aims to build responsible AI systems that are beneficial to society, with a particular emphasis on debiasing, robustness, and fairness in computer vision domain. I have explored debiasing tasks in classification models and have recently expanded my interests to address societal bias in models trained on large-scale datasets, particularly diffusion-based text-to-image models.

Contact

  • jeonghoon_park [at] kaist.ac.kr

  • Bundang-gu, Seongnam-si, Gyeonggi-do, South Korea

Education

  • Ph.D. in Artifical Intelligence, 2022-present

    KAIST, Korea

    Advisor: Prof. Jaegul Choo

  • M.S. in Artifical Intelligence, 2020-2022

    KAIST, Korea

    Advisor: Prof. Jaegul Choo

  • B.S. in Computer Science, 2015-2020

    Korea University, Korea

Experience

  • Research Internship at Kakao Enterprise
    Aug. 2022 - Nov. 2022

    Conducted initial research on bias mitigation for image classification, contributing to the spatial guidance methodology published at CVPR 2024.

Publications

  • Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention

    Jeonghoon Park*, Juyoung Lee*, Chaeyeon Chung, Jaeseong Lee, Jaegul Choo, Jindong Gu

    International Conference on Computer Vision (ICCV), 2025

    Paper | Code

  • Disentangling Subject-Irrelevant Elements against Subject in Personalized Text-to-Image Diffusion via Filtered Self-distillation

    Seunghwan Choi, Jooyeol Yun, Jeonghoon Park, and Jaegul Choo

    Winter Conference on Applications of Computer Vision (WACV), 2025

    Paper

  • Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair

    Jeonghoon Park*, Chaeyeon Chung*, Juyoung Lee, Jaegul Choo

    Proceedings of the IEEE/CVF Converence on Computer Vision and Pattern Recognition (CVPR), 2024

    Paper

  • BiasEnsemble: Revisiting the Importance of Amplifying Bias for Debiasing

    Jungsoo Lee*, Jeonghoon Park*, Daeyoung Kim*, Juyoung Lee, Edward Choi, Jaegul Choo

    AAAI Conference on Artificial Intelligence (AAAI), 2023

    Accepted as Oral Presentation (19.6% acceptance rate)

    Paper | Code

  • Training auxiliary prototypical classifiers for explainable anomaly detection in medical image segmentation

    Wonwoo Cho, Jeonghoon Park, Jaegul Choo

    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023

    Paper

  • Deep Edge-Aware Interactive Colorization against Color-Bleeding Effects

    Eungyeup Kim*, Sanghyeon Lee*, Jeonghoon Park*, Somi Choi, Choonghyun Seo, Jaegul Choo

    Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2021

    Accepted as Oral Presentation (3% acceptance rate)

    Paper | Project Page

  • Natural Attribute-based Shift Detection

    Jeonghoon Park*, Jimin Hong*, Radhika Dua*, Daehoon Gwak, Yixuan Li, Jaegul Choo, Edward Choi

    arXiv, 2021

    Paper

  • Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment

    Jeonghoon Park*, Kyungmin Jo*, Daehoon Gwak*, Jimin Hong, Jaegul Choo, Edward Choi

    NeurIPS 2020 Workshop: Self-Supervised Learning - Theory and Practice

    Paper