I am a Ph. D. student in the Computer Vision Lab at Seoul National University, advised by Bohyung Han. My researsh interest lies in computer vision and machine learning. I am interested in developing robust models that excel in real-world, uncontrolled environments through robust and scalable training techniques. My recent work has focused on federated learning and open-set recognition.

Contact: snow1234 (at) snu (dot) ac (dot) com

[2024. 03]   📃 Two papers on federated learning are accepted in CVPR 2024
[2023. 03]   📃 One paper on open-set learning is accepted in CVPR 2023
[2022. 05]   📃 One paper on federated learning is accepted in ICML 2022

• M.S. & Ph.D. Electrical and Computer Engineering, Seoul National University (Mar. 2019 - Current)
  • Computer Vision Lab
  • Advisors: Bohyung Han
• B.S. Electrical Engineering, Korea University (Mar. 2014 - Feb. 2019)

• Relaxed Contrastive Learning for Federated Learning
  Seonguk Seo*, Jinkyu Kim*, Geeho Kim*, and Bohyung Han
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
• Communication-Efficient Federated Learning with Accelerated Client Gradient
  Geeho Kim*, Jinkyu Kim*, and Bohyung Han
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
• Open-Set Representation Learning through Combinatorial Embedding
  Geeho Kim, Junoh Kang, and Bohyung Han
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
• Multi-level branched regularization for federated learning
  Jinkyu Kim*, Geeho Kim*, and Bohyung Han
  International Conference on Machine Learning (ICML), 2022
• Learning to optimize domain specific normalization for domain generalization
  Seonguk Seo, Yumin Suh, Dongwan Kim, Geeho Kim, and Bohyung Han
  European Conference on Computer Vision (ECCV), 2020
• Combinatorial inference against label noise
  Paul Hongsuck Seo, Geeho Kim, and Bohyung Han
  Advances in Neural Information Processing Systems (NeurIPS), 2019

• Qualcomm Innovations Fellowship Korea (2021)
• Best paper finalist with “Open-Set Representation Learning through Combinatorial Embedding”
• Visual Domain Adaptation Challenge (VisDA-19) (2019)
• ICCV 2019, 3rd Place Winner

• Regular Program Committee Member (Reviewer) in CVPR, NeurIPS, ICLR, ICML, ICCV and ECCV