Fully Self-Supervised Out-of-Domain Few-Shot Learning with Masked Autoencoders

Fully Self-Supervised Out-of-Domain Few-Shot Learning with Masked Autoencoders

Few-shot learning aims to identify unseen classes with limited labelled data. Recent few-shot learning techniques have shown success in generalizing to unseen classes; however, the performance of these techniques has also been shown to degrade when tested on an out-of-domain setting. Previous work,...

Full description

Bibliographic Details
Main Authors: Reece Walsh, Islam Osman, Omar Abdelaziz, Mohamed S. Shehata
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Journal of Imaging
Subjects:
few-shot learning
self-supervised
image classification
out-of-domain
Online Access:https://www.mdpi.com/2313-433X/10/1/23

Internet

https://www.mdpi.com/2313-433X/10/1/23

Similar Items