Open Collections

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

Multidisciplinary Digital Publishing Institute

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, additionally, has also demonstrated increasing reliance on supervised finetuning in an off-line or online capacity. This paper proposes a novel, fully self-supervised few-shot learning technique (FSS) that utilizes a vision transformer and masked autoencoder. The proposed technique can generalize to out-of-domain classes by finetuning the model in a fully self-supervised method for each episode. We evaluate the proposed technique using three datasets (all out-of-domain). As such, our results show that FSS has an accuracy gain of 1.05%, 0.12%, and 1.28% on the ISIC, EuroSat, and BCCD datasets, respectively, without the use of supervised training.

Article

eng

Vancouver : University of British Columbia Library

10.14288/1.0440608

Science, Irving K. Barber Faculty of (Okanagan); Computer Science, Mathematics, Physics and Statistics, Department of (Okanagan)

10.3390/jimaging10010023

Faculty

DSpace