P-PseudoLabel: Enhanced Pseudo-Labeling Framework With Network Pruning in Semi-Supervised Learning

P-PseudoLabel: Enhanced Pseudo-Labeling Framework With Network Pruning in Semi-Supervised Learning

Semi-supervised learning (SSL) methods for classification tasks exhibit a significant performance gain because they combine regularization and pseudo-labeling methods. General pseudo-labeling methods only depend on the model’s prediction when assigning pseudo-labels, but this approach oft...

Full description

Bibliographic Details
Main Authors: Gyeongdo Ham, Yucheol Cho, Jae-Hyeok Lee, Daeshik Kim
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Consistency regularization
network pruning
negative learning
pseudo labeling
semi-supervised learning
Online Access:https://ieeexplore.ieee.org/document/9932581/

Internet

https://ieeexplore.ieee.org/document/9932581/

Similar Items