MetaInfoNet: Learning Task-Guided Information for Sample Reweighting

Hongxin Wei
Hongxin Wei
Rundong Wang
Rundong Wang
Cited by: 0|Bibtex|Views15
Other Links: arxiv.org

Abstract:

Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance. Meta-learning algorithms are commonly designed to alleviate this issue in the form of sample reweighting, by learning a meta weighting network that takes training losses as inputs to generate sample weights. In this paper,...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments