Inkyu Shin

MS Candidate

Future Vehicle Engineering, KAIST

CV | Google Scholar | Github

I am a MS student advised by Professor In So Kweon, at Future Vehicle Engineering, KAIST.

My research interests currently lie in computer vision. Specifically, I pursue the goal to build domain adaptive recognition in computer vision, which handles data hungry problem in deep learning. My research topics include Unsupervised domain adaptation / Self-supervised learning.

Contact

dlsrbgg33 [at] kaist.ac.kr

dlsrbgg33 [at] gmail.com
Bldg N1, Rm 211, 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141

Education

BS in Future Vehicle Engineering, 2019

HYU, Korea

Research Experiences

Korea University, Seoul, Korea

Sep 2018 - Dec 2018

Research Intern, Data and Visual Analytics Lab.
Hanyang University, Seoul, Korea

Jul 2018 - Aug 2018

Research Assistant, Automotive Control and Electronics Laboratory.
Samsung Electronics., Hwasung,
Jan 2018 - Mar 2018

Research Intern, Semi-conductor Test group.

Publications

Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

Kwanyong Park, Sanghyun Woo, Inkyu Shin, Inso Kweon

NeurIPS 2020

[ Paper ]
Two-phase Pseudo Label Densification for Self-training based Domain Adaptation

Inkyu Shin, Sanghyun Woo, Fei Pan, Inso Kweon

ECCV 2020

*Also presented at CVPR 2020 Workshop(VL3)

[ Paper ]
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision

Fei Pan, Inkyu Shin, Francois Rameau, Seokju Lee, Inso Kweon

CVPR 2020 [Oral]

[ Project page | Paper | Code ]
Image-to-image translation via group-wise deep whitening-and-coloring transformation

Wongwoong Cho, Sungha Choi, David Keetae Park, Inkyu Shin, Jaegul Choo

CVPR 2019 [Oral]

[ Paper | Code ]