Machine Intelligence & Data Science
(MIDAS) Laboratory
We are developing state-of-the-art AI & data science solutions for imaging, image processing, and computer vision, as well as improving their fundamental understanding.
Research Overview
Our research interests in data science include
-
AI & machine learning,
-
optimization, and
-
sampling
with past and current projects in imaging, image processing, and computer vision:
-
medical imaging,
-
computational photography, and
-
vision-based autonomous systems.
Latest Publications
Self-supervised regression learning
Regression that predicts continuous quantity is a central part of applications using computational imaging and computer vision technologies. The paper proposes a general self-supervised regression learning framework that enables learning regression neural networks with only input data, but without ground-truth target data.