NCSI: Learning from Synthetic Image Data

Status	Completed
Mentor Name	Hao Ji
Mentor's XSEDE Affiliation	Education Allocation
Mentor Has Been in XSEDE Community	4-5 years
Project Title	Learning from Synthetic Image Data
Summary	Training and testing deep learning models typically require a large amount of labeled data. However, annotating data is a time-consuming and labor-intensive task which has long been performed manually. In this project, we plan to investigate automated approaches to generating synthetic labeled image data for training deep learning models with minimum human intervention. We will examine the effectiveness of the use of synthetic data in image classification, segmentation, and/or object detection applications.
Job Description	The student will study approaches for synthetic data generation, use synthetic data to train deep learning models, and assess their effectiveness in image classification, segmentation, and/or object detection applications.
Computational Resources	XSEDE Bridges GPUs
Contribution to Community
Position Type	Learner
Training Plan	I will offer a "Machine Learning and Its Applications" course in the coming summer. This course will prepare the students with the necessary knowledge and skills in Deep Learning. I will teach the students how to use XSEDE for training. During this project, I will work closely with the students and plan to have weekly meetings with them to guide their research progress.
Student Prerequisites/Conditions/Qualifications	Must have an undergraduate at California State Polytechnic University, Pomona
Duration	Summer
Start Date	05/20/2019
End Date	08/16/2019