Low-shot learning and class imbalance: a survey

Low-shot learning and class imbalance: a survey

Abstract The tasks of few-shot, one-shot, and zero-shot learning—or collectively “low-shot learning” (LSL)—at first glance are quite similar to the long-standing task of class imbalanced learning; specifically, they aim to learn classes for which there is little labeled data available. Motivated by...

Full description

Bibliographic Details
Main Authors: Preston Billion Polak, Joseph D. Prusa, Taghi M. Khoshgoftaar
Format: Article
Language:English
Published: SpringerOpen 2024-01-01
Series:Journal of Big Data
Subjects:
Low-shot learning
Few-shot learning
Zero-shot learning
Class imbalance
Class-imbalanced learning
Machine learning
Online Access:https://doi.org/10.1186/s40537-023-00851-z

Internet

https://doi.org/10.1186/s40537-023-00851-z

Similar Items