Seunghun Lee

Ph.D. Student

lsh5688 at dgist.ac.kr

Research Interests

  • Generative Adversrial Networks
  • Image-to-Image Translation & Style Transfer
  • Domain Adaptation

Education

  • M.S.–Ph.D. Integrated Course in Electrical Engineering and Computer Science, DGIST, Mar 2019 – present.

Publication

  • Changjae Kim, Seunghun Lee, Sunghoon Im, “Multi-Target Domain Adaptation with Class-Wise Attribute Transfer in Semantic Segmentation,” The 34th British Machine Vision Conference (BMVC), 2024
  • Seunghun Lee, Wonhyeok Choi, Changjae Kim, Minwoo Choi, Sunghoon Im. “ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  • Seunghun Lee, Sunghyun Cho, and Sunghoon Im. “DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Scholarships & Awards

  • Participation Prize, 28th HumanTech Paper Award, Samsung Electronics Co., Ltd., Feb 2022.
  • 3rd place Prize at ICT Paper contest, Dec 2021.