Few-shot learning with relation propagation and constraint

Few-shot learning with relation propagation and constraint

Previous deep learning methods usually required large-scale annotated data, which is computationally exhaustive and unrealistic in certain scenarios. Therefore, few-shot learning, where only a few annotated training images are available for training, has attracted increasing attention these days, sh...

Full description

Bibliographic Details
Main Authors: Gong, H. (Author), Liu, W. (Author), Liu, X. (Author), Ma, Y. (Author), Wang, S. (Author), Yan, Y. (Author), Zhao, X. (Author)
Format: Article
Language:English
Published: John Wiley and Sons Inc 2021
Subjects:
computer vision
Computer vision
Constraint module
correlation methods
Correlation methods
Deep learning
Extraction
graph theory
Graph theory
image recognition
Image recognition
Large-scales
Learning methods
Preprocess
Propagation modules
Query processing
Relation propagation
Relational representations
Semantics
Shot classification
State of the art
Training image
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items