Self-Supervised Metric-Based Meta-Learning for Few-Shot Image classification

In this work, metric-based meta-learning models are proposed to learn a generic model embedding that can reduce the data shifting effect and thereby effectively distinguish the unseen samples. In addition, self-supervised learning is employed to mitigate the data scarcity problem by learning a robus...

Full description

Saved in:
Bibliographic Details
Main Author: Lim, Jit Yan
Format: Thesis
Published: 2022
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-mmu-ep.11546
record_format uketd_dc
spelling my-mmu-ep.115462023-07-18T06:05:12Z Self-Supervised Metric-Based Meta-Learning for Few-Shot Image classification 2022-12 Lim, Jit Yan Q300-390 Cybernetics In this work, metric-based meta-learning models are proposed to learn a generic model embedding that can reduce the data shifting effect and thereby effectively distinguish the unseen samples. In addition, self-supervised learning is employed to mitigate the data scarcity problem by learning a robust representation via increasing the training samples with different structural information. In this study, three novel selfsupervised metric-based meta-learning methods namely: (1) Self-supervised Learning Prototypical Networks (SLPN), (2) Self-supervised Contrastive Representation Learning (SCRL), and (3) Self-supervised Fused Representation Learning (SFRL), are proposed for few-shot image classification. The proposed SLPN enhances the intra-class discriminability via contrastive-based self-supervised learning to encounter the data shifting issue. For the proposed SCRL, the intra-class diversity is enriched via the auxiliary signal from distortion-based self-supervised learning to solve the overfitting issue in the low-data regime. As for the proposed SFRL, task-specific information is exploited to better formulate the boundaries of the novel classes. The three proposed methods manage to improve the robustness of the model embedding toward samples from novel classes and eliminate the data shifting and data scarcity issues. The proposed meta-learning methods are evaluated on three benchmark fewshot image datasets, ie., miniImageNet, tieredImageNet, and CIFAR-FS. The experiments are conducted based on standard protocol that uses 5-way 1-shot and 5-way 5-shot settings. From the experiment results, all proposed metric-based meta-learning methods successfully outperform the state-of-the-art approaches on all three benchmark few-shot image classification datasets. 2022-12 Thesis http://shdl.mmu.edu.my/11546/ http://erep.mmu.edu.my/ phd doctoral Multimedia University Faculty of Information Science and Technology (FIST) EREP ID: 10857
institution Multimedia University
collection MMU Institutional Repository
topic Q300-390 Cybernetics
spellingShingle Q300-390 Cybernetics
Lim, Jit Yan
Self-Supervised Metric-Based Meta-Learning for Few-Shot Image classification
description In this work, metric-based meta-learning models are proposed to learn a generic model embedding that can reduce the data shifting effect and thereby effectively distinguish the unseen samples. In addition, self-supervised learning is employed to mitigate the data scarcity problem by learning a robust representation via increasing the training samples with different structural information. In this study, three novel selfsupervised metric-based meta-learning methods namely: (1) Self-supervised Learning Prototypical Networks (SLPN), (2) Self-supervised Contrastive Representation Learning (SCRL), and (3) Self-supervised Fused Representation Learning (SFRL), are proposed for few-shot image classification. The proposed SLPN enhances the intra-class discriminability via contrastive-based self-supervised learning to encounter the data shifting issue. For the proposed SCRL, the intra-class diversity is enriched via the auxiliary signal from distortion-based self-supervised learning to solve the overfitting issue in the low-data regime. As for the proposed SFRL, task-specific information is exploited to better formulate the boundaries of the novel classes. The three proposed methods manage to improve the robustness of the model embedding toward samples from novel classes and eliminate the data shifting and data scarcity issues. The proposed meta-learning methods are evaluated on three benchmark fewshot image datasets, ie., miniImageNet, tieredImageNet, and CIFAR-FS. The experiments are conducted based on standard protocol that uses 5-way 1-shot and 5-way 5-shot settings. From the experiment results, all proposed metric-based meta-learning methods successfully outperform the state-of-the-art approaches on all three benchmark few-shot image classification datasets.
format Thesis
qualification_name Doctor of Philosophy (PhD.)
qualification_level Doctorate
author Lim, Jit Yan
author_facet Lim, Jit Yan
author_sort Lim, Jit Yan
title Self-Supervised Metric-Based Meta-Learning for Few-Shot Image classification
title_short Self-Supervised Metric-Based Meta-Learning for Few-Shot Image classification
title_full Self-Supervised Metric-Based Meta-Learning for Few-Shot Image classification
title_fullStr Self-Supervised Metric-Based Meta-Learning for Few-Shot Image classification
title_full_unstemmed Self-Supervised Metric-Based Meta-Learning for Few-Shot Image classification
title_sort self-supervised metric-based meta-learning for few-shot image classification
granting_institution Multimedia University
granting_department Faculty of Information Science and Technology (FIST)
publishDate 2022
_version_ 1776101417759539200