Label propagation via local geometry preserving for deep semi-supervised image recognition
In this paper, we propose a novel transductive pseudo-labeling based method for deep semi-supervised image recognition. Inspired from the superiority of pseudo labels inferred by label propagation compared with those inferred from network, we argue that information flow from labeled data to unlabele...
Saved in:
Main Authors: | Qing, Yuanyuan, Zeng, Yijie, Huang, Guang-Bin |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/160771 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
DML-PL: deep metric learning based pseudo-labeling framework for class imbalanced semi-supervised learning
by: Yan, Mi, et al.
Published: (2023) -
A comparison of methods for data-driven cancer outlier discovery, and an application scheme to semisupervised predictive biomarker discovery
by: Karrila, S., et al.
Published: (2014) -
Toward the optimization of normalized graph Laplacian
by: Xie, B., et al.
Published: (2013) -
Delving into important samples of semi-supervised old photo restoration: A new dataset and method
by: CAI, Werwei, et al.
Published: (2024) -
Relation extraction using label propagation based semi-supervised learning
by: Chen, J., et al.
Published: (2013)