Few-shot Learning: Methods and Applications
The Few-shot learning (FSL) approach distills meaningful features from a constrained sample set, allowing models to swiftly adjust to novel tasks and decreasing the dependency on extensive datasets. This approach leverages methods involving meta-learning, transfer learning, and data augmentation to...
Saved in:
Main Authors: | Li Jiaxiang, Li Mingyang |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2025-01-01
|
Series: | ITM Web of Conferences |
Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_02012.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Learning under label noise through few-shot human-in-the-loop refinement
by: Aaqib Saeed, et al.
Published: (2025-02-01) -
LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging
by: Charilaos Papaioannou, et al.
Published: (2025-01-01) -
SSL-MBC: Self-Supervised Learning With Multibranch Consistency for Few-Shot PolSAR Image Classification
by: Wenmei Li, et al.
Published: (2025-01-01) -
A Few Misconceptions about Cultural Evolution
by: O’Brien Michael J.
Published: (2010-12-01) -
A deep learning-based method for the intelligent identification of the quantity of coals flushed out during borehole hydraulic flushing
by: Xiaojun LI, et al.
Published: (2025-01-01)