Inyoung Cho
Hi, I'm a master's student in the Scalable Graphics, Vision, & Robotics Lab at KAIST's School of Computing. Before that, I earned my B.S. from KAIST.
Research Interests
Physically-based Rendering, Deep Learning
Education
M.S., Computer Science, KAIST. Sep. 2019 - Present
- GPA: 4.25/4.3
B.S., Computer Science and Mathematics (double major), KAIST. Mar. 2015 - Aug. 2019
- Summa Cum Laude (GPA: 4.0/4.3)
Publications
Monte Carlo Reconstruction
2020.02 ~ 2021.02
Coming soon.
Personal Projects
OptaGen: OptiX-based Automated Dataset Generator
2019.10 ~ 2020.03
Sorry! This work is private yet. The public version will release soon. Stay tuned!
Nvidia OptiX is a promising GPU-based ray-tracing SDK.
I am currently implementing an OptiX-based program that automatically generates rendered images especially for training deep convolutional denoising models.
The program will involve random camera transformations, random material changes, auxiliary buffer processing, etc.
Reproduction of Published Papers
Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy
Qing Yu, Kiyoharu Aizawa
In ICCV, 2019
In this paper, the authors propose a two-headed neural network and maximize the discrepancy between the two classifiers to detect out-of-distribution samples while correctly classifying in-distribution inputs. Also, they suggest a new problem setting where they utilize unlabeled data for unsupervised training, whereas previous works only exploit labeled in-distribution samples.
Learning Loss for Active Learning
Donggeun Yoo, In So Kweon
In CVPR, 2019
In this paper, the authors propose a task-agnostic and straightforward active learning technique. They build a “loss prediction module” that predicts target losses of unlabeled inputs. Using this predicted loss as an uncertainty measure, they determined which of the unlabeled data would be most valuable to annotate.
