Enhancing image segmentation with point prompt augmentation

Enhancing image segmentation with point prompt augmentation

This project aims to make use of point prompt augmentation techniques to enhance and improve the image segmentation performance of the Segment Anything Model 2 (SAM2). Using SAMAug as a framework for point augmentation strategies, different point generation methods were used when training on the Vec...

Full description

Saved in:
Bibliographic Details
Main Author: Pai, Hrishikesh Harish
Other Authors: Lin Guosheng
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Computer and Information Science
Segmentation
Augmentation
Online Access:https://hdl.handle.net/10356/181188
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-181188
record_format dspace
spelling sg-ntu-dr.10356-1811882024-11-18T02:15:52Z Enhancing image segmentation with point prompt augmentation Pai, Hrishikesh Harish Lin Guosheng College of Computing and Data Science gslin@ntu.edu.sg Computer and Information Science Segmentation Augmentation This project aims to make use of point prompt augmentation techniques to enhance and improve the image segmentation performance of the Segment Anything Model 2 (SAM2). Using SAMAug as a framework for point augmentation strategies, different point generation methods were used when training on the Vector-LabPics dataset. The report will explore these techniques (random sampling, entropy-based sampling, distance based sampling) as well as evaluate the performance of the baseline SAM2, against SAM2 with data augmentation incorporated during training. Bachelor's degree 2024-11-18T02:15:17Z 2024-11-18T02:15:17Z 2024 Final Year Project (FYP) Pai, H. H. (2024). Enhancing image segmentation with point prompt augmentation. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/181188 https://hdl.handle.net/10356/181188 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 Computer and Information Science
Segmentation
Augmentation
spellingShingle Computer and Information Science
Segmentation
Augmentation
Pai, Hrishikesh Harish
Enhancing image segmentation with point prompt augmentation
description This project aims to make use of point prompt augmentation techniques to enhance and improve the image segmentation performance of the Segment Anything Model 2 (SAM2). Using SAMAug as a framework for point augmentation strategies, different point generation methods were used when training on the Vector-LabPics dataset. The report will explore these techniques (random sampling, entropy-based sampling, distance based sampling) as well as evaluate the performance of the baseline SAM2, against SAM2 with data augmentation incorporated during training.
author2 Lin Guosheng
author_facet Lin Guosheng
Pai, Hrishikesh Harish
format Final Year Project
author Pai, Hrishikesh Harish
author_sort Pai, Hrishikesh Harish
title Enhancing image segmentation with point prompt augmentation
title_short Enhancing image segmentation with point prompt augmentation
title_full Enhancing image segmentation with point prompt augmentation
title_fullStr Enhancing image segmentation with point prompt augmentation
title_full_unstemmed Enhancing image segmentation with point prompt augmentation
title_sort enhancing image segmentation with point prompt augmentation
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/181188
_version_ 1816858966602285056

Similar Items