Explore the influential samples in domain generalization
Domain Generalization (DG) aims to learn a model that generalizes in testing domains unseen from training. All DG methods assume that the domain-invariant features can be learned by discarding the domain-specific ones. However, in practice, the learned invariant features usually contain "spurio...
Saved in:
Main Author: | Wu, Zike |
---|---|
Other Authors: | Hanwang Zhang |
Format: | Thesis-Master by Research |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172753 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Lightweight surveillance systems on embedded domains
by: Tan, Jun Han
Published: (2022) -
Unsupervised domain adaptation for LiDAR segmentation
by: Kong, Lingdong
Published: (2022) -
Camera domain transfer for video-based person re-identification
by: Ding, Bangjie
Published: (2022) -
An investigation over the state-of-the-art unsupervised domain adaptation person re-identification
by: Xiao, Yang
Published: (2022) -
Exploring higher quality point clouds using stereo vision
by: Foo, Chuan Ann
Published: (2022)