Robust and generalized methods for medical image analysis
Project Description
This project will cover topics about model robustness and generalization. For example, how to make a deep learning model perform well even on unseen data distributions. This project provides solutions on existing medical image diagnosis, where the test data sometimes is from unknown distributions.
Supervisor
LI Xiaomeng
Quota
10
Course type
UROP1000
UROP1100
UROP2100
UROP3100
UROP4100
Applicant's Roles
1, Students will understand AI, machine learning, and deep learning.
2, They will perform experiments, read papers and discuss ideas with supervisors.
2, They will perform experiments, read papers and discuss ideas with supervisors.
Applicant's Learning Objectives
1. Students are expected to have a deep understanding of robustness and generalization in deep learning.
2. They are expected to know the existing research, including both the advantages and disadvantages.
3, They should be able to have their own ideas for solving cutting-edge problems and have research outcomes.
2. They are expected to know the existing research, including both the advantages and disadvantages.
3, They should be able to have their own ideas for solving cutting-edge problems and have research outcomes.
Complexity of the project
Moderate