Adaptive deep few-shot learning

Machine learning (ML) techniques have been successfully implemented in many fields with the absence of sufficient and high-quality data, such as computer vision (CV) tasks. However, the performance of ML techniques may be derogated due to the presence of insufficient data. Regarding the problem of t...

Full description

Saved in:
Bibliographic Details
Main Author: Gu, Rong
Other Authors: Wen Bihan
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/172615
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-172615
record_format dspace
spelling sg-ntu-dr.10356-1726152023-12-22T15:45:33Z Adaptive deep few-shot learning Gu, Rong Wen Bihan School of Electrical and Electronic Engineering bihan.wen@ntu.edu.sg Engineering::Electrical and electronic engineering Machine learning (ML) techniques have been successfully implemented in many fields with the absence of sufficient and high-quality data, such as computer vision (CV) tasks. However, the performance of ML techniques may be derogated due to the presence of insufficient data. Regarding the problem of this aspect, Few-shot learning (FSL) has been developed recently to solve the problem caused by the mismatch between the quantity of current dataset and ideal dataset respectively. In this dissertation, we study the architecture of various convolutional neural networks like Visual Geometry Group (VGG) and residual neural networks (ResNet) and implement FSL in image classification based on different VGG neural networks and ResNets. The classification accuracy ranges from 22.32% to 98.72% with different neural networks as the feature extraction network. The result of most experiments is above 92.01%, which shows the efficient image classification ability of ResNets and VGG neural networks in FSL. Master of Science (Computer Control and Automation) 2023-12-18T00:26:54Z 2023-12-18T00:26:54Z 2023 Thesis-Master by Coursework Gu, R. (2023). Adaptive deep few-shot learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/172615 https://hdl.handle.net/10356/172615 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
spellingShingle Engineering::Electrical and electronic engineering
Gu, Rong
Adaptive deep few-shot learning
description Machine learning (ML) techniques have been successfully implemented in many fields with the absence of sufficient and high-quality data, such as computer vision (CV) tasks. However, the performance of ML techniques may be derogated due to the presence of insufficient data. Regarding the problem of this aspect, Few-shot learning (FSL) has been developed recently to solve the problem caused by the mismatch between the quantity of current dataset and ideal dataset respectively. In this dissertation, we study the architecture of various convolutional neural networks like Visual Geometry Group (VGG) and residual neural networks (ResNet) and implement FSL in image classification based on different VGG neural networks and ResNets. The classification accuracy ranges from 22.32% to 98.72% with different neural networks as the feature extraction network. The result of most experiments is above 92.01%, which shows the efficient image classification ability of ResNets and VGG neural networks in FSL.
author2 Wen Bihan
author_facet Wen Bihan
Gu, Rong
format Thesis-Master by Coursework
author Gu, Rong
author_sort Gu, Rong
title Adaptive deep few-shot learning
title_short Adaptive deep few-shot learning
title_full Adaptive deep few-shot learning
title_fullStr Adaptive deep few-shot learning
title_full_unstemmed Adaptive deep few-shot learning
title_sort adaptive deep few-shot learning
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/172615
_version_ 1787136620975095808