Avatar

Wooju Lee

Ph.D. Candidate

KAIST


CV | Google Scholar


I am a Ph.D. student advised by Professor Hyun Myung at KAIST.

My research interests lie in machine learning and computer vision, with particular focus on domain generalization. Domain generalization deals with a challenging problem that generalize the model without any access to unseen domains in the training process. My ultimate goal is generalizing deep neural networks for 2D RGB images, 3D point clouds, and SLAM. My previous published works span adversarial attacks and bio-inspired robust deep learning.

Contact

  • dnwn24 [at] kaist.ac.kr

  • E3-2, 3240, 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141

Education

  • B.S in Mechanical Engineering, 2019

    Korea University, Korea

  • M.S in Robotics Program, 2021

    KAIST, Korea

Publications

  • Adversarial Attack for Asynchronous Event-based Data

    Wooju Lee, Hyun Myung

    AAAI 2022 (Acceptance rate: 1349/9020 ≈ 15%)

    [ Paper / Code ]

  • Adaptive Coverage Path Planning Policy for a Cleaning Robot with Deep Reinforcement Learning

    DongKi Noh, WooJu Lee, Hyoung-Rock Kim, Il-Soo Cho, In-Bo Shim and SeungMin Baek

    ICCE 2022

    [ Paper / Code ]

  • 이미지를 강인하게 인식하는 중심주변 조절 기반 뉴럴 네트워크

    Wooju Lee, Hyun Myung

    KRoC 2021

    [ Paper / Code ]

Awards

  • AFCV (Asian Federation of Computer Vision) Best Paper Award, KRoC '21

Academic Activities

Reviewer