Reducing Uncertainty of Weak Supervised Signals via Mutual Information Techniques

Reducing Uncertainty of Weak Supervised Signals via Mutual Information Techniques

Weakly supervised learning (WSL) refers to training models using imperfect or noisy labels, which can significantly reduce the costs associated with manual labeling. However, the model performance may be affected by the uncertainty of weakly supervised signals (WSS). To address this problem, we prop...

Full description

Saved in:
Bibliographic Details
Main Authors: Yichen Liu, Hanlin Feng, Xin Zhang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Weakly supervised learning
mutual information
image classification
variational approximation
random projection
Online Access:https://ieeexplore.ieee.org/document/10908221/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10908221/

Similar Items