Removing bias for out-of-distribution generalization

Deep models have a strong ability to fit the training data, and thus can achieve high performance when the testing data is sampled from the same distribution as the training. However, in practice, the deep models fail to perform perfectly because the testing data is usually Out-of-Distribution (OOD)...

Full description

Saved in:
Bibliographic Details
Main Author: Qi, Jiaxin
Other Authors: Zhang Hanwang
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/168654
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Be the first to leave a comment!
You must be logged in first