Towards Safe Weakly Supervised Learning

In this paper, we study weakly supervised learning where a large amount of data supervision is not accessible. This includes i) incomplete supervision, where only a small subset of labels is given, such as semi-supervised learning and domain adaptation; ii) inexact supervision, where only coarse-gra...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2021-01, Vol.43 (1), p.334-346
Main Authors: Li, Yu-Feng, Guo, Lan-Zhe, Zhou, Zhi-Hua
Format: Article
Language:English
Subjects:
Adaptation
Cognitive tasks
domain adaptation
Domains
label noise learning
Labels
Machine learning
multi-instance learning
Optimization
Performance gain
Proposals
safe
semi-supervised learning
Semisupervised learning
Supervised learning
Supervision
Task analysis
Training data
Weakly supervised learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!