Github
I am a Master candidate in Robotics and Computer Vision Lab at Korea Advanced Institute of Science and Technology (KAIST) under the supervision of Prof. In So Kweon since 2019. I received B.S in automotive engineering from Hanyang University (HYU).
My major interests currently lay in domain adaptive recognition in computer vision, which handles data hungry problem in deep learning.
Inkyu Shin
Computer vision Researcher
Lab homepage
Address
291, Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea
Research Interest
Computer Vision, Deep Learning
-
Image Translation
-
Domain Adaptive Recognition (Image, Video)
Publication
Two-phase Pseudo Label Densification for Self-training based Domain Adaptation
Inkyu Shin, Sanghyun Woo, Fei pan, In So Kweon
European Conference on Computer Vision (ECCV), 2020.
Paper
-
Also Presented at "Visual Learning with Limited Labels" Workshops in conjunction with CVPR 2020
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
Fei pan, Inkyu Shin, Francois Rameau, Seokju Lee, In So Kweon
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
(Oral)
Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation
Wonwoong Cho, Sungha Choi, David Keetae Park, Inkyu Shin, Jaegul Choo
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
(Oral)
Internship
-
Research Internship in DAVIAN Lab, Korea university
- Topic: Image to Image Translation
-
Computer vision research
-
2018/09 ~ 2018/12
-
Undergraduate Researcher in ACE Lab
-
Autonomous Driving
- Topic: Generating lanelet
-
2018/11 ~ 2018/12
-
Internship in Samsung Electronics
-
2017/12 ~ 2018/02
Awards
-
Autonomous modeled car contest
-
Honorable awards / Mathworks special awards
-
2018/06
Code