Self-supervised deep learning for missing image predictions

Deep learning has revolutionised the field of computer vision, enabling impressive advances in image classification, object detection, and segmentation. However, the success of supervised deep learning in computer vision is largely dependent on the availability of large annotated datasets, which can...

Full description

Saved in:
Bibliographic Details
Main Author: Yeoh, Shun Bin
Other Authors: Yeo Chai Kiat
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/166706
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-166706
record_format dspace
spelling sg-ntu-dr.10356-1667062023-05-12T15:36:57Z Self-supervised deep learning for missing image predictions Yeoh, Shun Bin Yeo Chai Kiat School of Computer Science and Engineering ASCKYEO@ntu.edu.sg Engineering::Computer science and engineering Deep learning has revolutionised the field of computer vision, enabling impressive advances in image classification, object detection, and segmentation. However, the success of supervised deep learning in computer vision is largely dependent on the availability of large annotated datasets, which can be time- consuming and expensive to acquire. Hence, self-supervised deep learning can be automated even with enormous volumes of unlabelled data, which reduces data labelling costs. This project explores self-supervised learning techniques for computer vision-based tasks, with a specific focus on patch context prediction for missing image predictions. We explore the potential of self-supervised learning to develop a model that can predict missing parts of an image based on the surrounding context and evaluate the performance of state-of-the-art (SOTA) techniques in this area. The goal of this report is to demonstrate the potential of self-supervised learning for practical image restoration scenarios and to provide insights into the impact of hyperparameters on model performance. Bachelor of Engineering (Computer Science) 2023-05-09T07:46:33Z 2023-05-09T07:46:33Z 2023 Final Year Project (FYP) Yeoh, S. B. (2023). Self-supervised deep learning for missing image predictions. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166706 https://hdl.handle.net/10356/166706 en SCSE22-0243 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::Computer science and engineering
spellingShingle Engineering::Computer science and engineering
Yeoh, Shun Bin
Self-supervised deep learning for missing image predictions
description Deep learning has revolutionised the field of computer vision, enabling impressive advances in image classification, object detection, and segmentation. However, the success of supervised deep learning in computer vision is largely dependent on the availability of large annotated datasets, which can be time- consuming and expensive to acquire. Hence, self-supervised deep learning can be automated even with enormous volumes of unlabelled data, which reduces data labelling costs. This project explores self-supervised learning techniques for computer vision-based tasks, with a specific focus on patch context prediction for missing image predictions. We explore the potential of self-supervised learning to develop a model that can predict missing parts of an image based on the surrounding context and evaluate the performance of state-of-the-art (SOTA) techniques in this area. The goal of this report is to demonstrate the potential of self-supervised learning for practical image restoration scenarios and to provide insights into the impact of hyperparameters on model performance.
author2 Yeo Chai Kiat
author_facet Yeo Chai Kiat
Yeoh, Shun Bin
format Final Year Project
author Yeoh, Shun Bin
author_sort Yeoh, Shun Bin
title Self-supervised deep learning for missing image predictions
title_short Self-supervised deep learning for missing image predictions
title_full Self-supervised deep learning for missing image predictions
title_fullStr Self-supervised deep learning for missing image predictions
title_full_unstemmed Self-supervised deep learning for missing image predictions
title_sort self-supervised deep learning for missing image predictions
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/166706
_version_ 1770564072396292096