2023
DOI: 10.1016/j.displa.2023.102370
|View full text |Cite
|
Sign up to set email alerts
|

COVID-19 chest X-ray image classification in the presence of noisy labels

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 10 publications
(1 citation statement)
references
References 47 publications
0
1
0
Order By: Relevance
“…(1) Due to the intrinsic correlation between multiple diseases, the potential semantic relationships between diseases can be explored by introducing Transformer as a priori knowledge. (2) Resolving the uncertainty of the presence of noise labels: most of the existing classification methods ignore the problem that labels are hardly completely realistic and valid [ 47 ]. Multiple levels of weight assignment and replacement can be applied to the tags to eliminate noise and thus reduce the interference of noisy tags.…”
Section: Discussionmentioning
confidence: 99%
“…(1) Due to the intrinsic correlation between multiple diseases, the potential semantic relationships between diseases can be explored by introducing Transformer as a priori knowledge. (2) Resolving the uncertainty of the presence of noise labels: most of the existing classification methods ignore the problem that labels are hardly completely realistic and valid [ 47 ]. Multiple levels of weight assignment and replacement can be applied to the tags to eliminate noise and thus reduce the interference of noisy tags.…”
Section: Discussionmentioning
confidence: 99%