Domain adaption for semantic segmentation

Semantic Segmentation is regarded as one of the most challenging and high-level problem, in computer vision. It allows for greater sense of image understanding, allows for it to have a wide variety of application spanning from medical image processing to autonomous driving, which would be the focus...

Full description

Saved in:
Bibliographic Details
Main Author: Saklani Pankaj
Other Authors: Lin Guosheng
Format: Final Year Project
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/76950
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-76950
record_format dspace
spelling sg-ntu-dr.10356-769502023-03-03T20:46:30Z Domain adaption for semantic segmentation Saklani Pankaj Lin Guosheng School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering Semantic Segmentation is regarded as one of the most challenging and high-level problem, in computer vision. It allows for greater sense of image understanding, allows for it to have a wide variety of application spanning from medical image processing to autonomous driving, which would be the focus of the project. Since many applications share common features and thus can be trained on the same datasets, however, all of them do not share the application domain and thus might have several deviations from the training dataset, such as illumination, geographical location, image quality. This project will discuss the use of domain adaption in the context of semantic segmentation, creating and evaluation a Convolutional Neural Network model to train on Berkley Deep Drive Dataset and through domain adaption, perform semantic segmentation on ApolloScape Dataset. The report will elaborate on the domain adaption technique Maximum Mean Discrepancy, the data pre-processing methods, the data augmentation methods, and the architecture of the model created. The training hyper-parameters, system configuration would also be presented in the report. Furthermore, the evaluation matrix, problems encountered, and results of the project will be discussed upon, in the report. Though this evaluation, it was discovered that the proposed model was successful in showcasing that the domain adaption technique has greater accuracy that normal segmentation model that do the same task. Bachelor of Engineering (Computer Science) 2019-04-25T07:13:50Z 2019-04-25T07:13:50Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/76950 en Nanyang Technological University 46 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Saklani Pankaj
Domain adaption for semantic segmentation
description Semantic Segmentation is regarded as one of the most challenging and high-level problem, in computer vision. It allows for greater sense of image understanding, allows for it to have a wide variety of application spanning from medical image processing to autonomous driving, which would be the focus of the project. Since many applications share common features and thus can be trained on the same datasets, however, all of them do not share the application domain and thus might have several deviations from the training dataset, such as illumination, geographical location, image quality. This project will discuss the use of domain adaption in the context of semantic segmentation, creating and evaluation a Convolutional Neural Network model to train on Berkley Deep Drive Dataset and through domain adaption, perform semantic segmentation on ApolloScape Dataset. The report will elaborate on the domain adaption technique Maximum Mean Discrepancy, the data pre-processing methods, the data augmentation methods, and the architecture of the model created. The training hyper-parameters, system configuration would also be presented in the report. Furthermore, the evaluation matrix, problems encountered, and results of the project will be discussed upon, in the report. Though this evaluation, it was discovered that the proposed model was successful in showcasing that the domain adaption technique has greater accuracy that normal segmentation model that do the same task.
author2 Lin Guosheng
author_facet Lin Guosheng
Saklani Pankaj
format Final Year Project
author Saklani Pankaj
author_sort Saklani Pankaj
title Domain adaption for semantic segmentation
title_short Domain adaption for semantic segmentation
title_full Domain adaption for semantic segmentation
title_fullStr Domain adaption for semantic segmentation
title_full_unstemmed Domain adaption for semantic segmentation
title_sort domain adaption for semantic segmentation
publishDate 2019
url http://hdl.handle.net/10356/76950
_version_ 1759853321626058752