Jun Seo

Bio

Jun Seo received the B.S. and M.S. degrees in electrical engineering from the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea, in 2016 and 2018. He is currently studying as Ph.D candidate in KAIST, with Prof. Jaekyun Moon. His research interest is machine learning, including meta learning and few-shot learning.

News

  • [10/2020] Our work on few-shot segmentation using feature transformation is on arXiv

  • [09/2020] Our work on few-round learning for communication-efficient federated learning has been submitted to International Conference on Learning Representations (ICLR)

  • [09/2020] Our work on few-shot semantic edge detection has been submitted to International Conference on Learning Representations (ICLR)

  • [06/2020] Our work on few-shot segmentation has been submitted to Conference on Neural Information Processing Systems (NeurIPS) 2020

  • [06/2020] Our work on incremental few-shot learning has been accepted to International Conference on Machine Learning (ICML) 2020: "XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning."

  • [11/2019] Our poster presentation on "TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning" won the best poster award in Samsung AI Forum 2019.

  • [04/2019] Our work on few-shot learning with Task-adaptive projection has been accepted to International Conference on Machine Learning (ICML) 2019: "TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning."

  • [09/2018] I won the Qualcomm Innovation Award.

  • [06/2018] Our work on meta-learning has been accepted to NeurIPS 2018 Workshop on Meta-Learning: "Meta Learner with Linear Nulling."