Adversarial cross-modal unsupervised domain adaptation in semantic segmentation
3D semantic segmentation is a vital problem in automatic driving, and thus a hot field in deep learning. These days, the research for unsupervised domain adaptation rises for solving the problem of lacking annotated datasets. However, the research on 3D UDA in semantic segmentation is still a blu...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/159248 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-159248 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1592482023-07-04T17:52:25Z Adversarial cross-modal unsupervised domain adaptation in semantic segmentation Shi, Mengqi Xie Lihua School of Electrical and Electronic Engineering ELHXIE@ntu.edu.sg Engineering::Electrical and electronic engineering 3D semantic segmentation is a vital problem in automatic driving, and thus a hot field in deep learning. These days, the research for unsupervised domain adaptation rises for solving the problem of lacking annotated datasets. However, the research on 3D UDA in semantic segmentation is still a blue sea. Our research aims to combine adversarial learning and cross-modal networks to boost the performance of 3D UDA across datasets in semantic segmentation. With this goal, we propose a new solution based on xMUDA and ADVENT, research several detailed change in this novel network and obtain better 3D and overall performances. In this dissertation, we use independent discriminators on cross-modal UDA networks. Firstly, we add uni-modal ones and get our best solution, which has a 3D mIoU 7.53% higher than the baseline and an improvement of overall performance by 3.68%. Then, we add two more cross-modal discriminators but the performance suffers a decrease. However, the performance is still better than the baseline. To research on the priority between MaxSqaureLoss and cross-modal loss in our aiming task, we design a pair of experiments and find cross-modal method act better in such tasks. Finally, in terms of the over-fitting issue occurring in both baseline and our method, we give our thoughts about the cause. Master of Science (Computer Control and Automation) 2022-06-08T05:27:31Z 2022-06-08T05:27:31Z 2022 Thesis-Master by Coursework Shi, M. (2022). Adversarial cross-modal unsupervised domain adaptation in semantic segmentation. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/159248 https://hdl.handle.net/10356/159248 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 Shi, Mengqi Adversarial cross-modal unsupervised domain adaptation in semantic segmentation |
description |
3D semantic segmentation is a vital problem in automatic driving, and thus a
hot field in deep learning. These days, the research for unsupervised domain
adaptation rises for solving the problem of lacking annotated datasets. However,
the research on 3D UDA in semantic segmentation is still a blue sea.
Our research aims to combine adversarial learning and cross-modal networks to
boost the performance of 3D UDA across datasets in semantic segmentation.
With this goal, we propose a new solution based on xMUDA and ADVENT,
research several detailed change in this novel network and obtain better 3D and
overall performances.
In this dissertation, we use independent discriminators on cross-modal UDA networks.
Firstly, we add uni-modal ones and get our best solution, which has a
3D mIoU 7.53% higher than the baseline and an improvement of overall performance
by 3.68%. Then, we add two more cross-modal discriminators but the
performance suffers a decrease. However, the performance is still better than the
baseline. To research on the priority between MaxSqaureLoss and cross-modal
loss in our aiming task, we design a pair of experiments and find cross-modal
method act better in such tasks.
Finally, in terms of the over-fitting issue occurring in both baseline and our
method, we give our thoughts about the cause. |
author2 |
Xie Lihua |
author_facet |
Xie Lihua Shi, Mengqi |
format |
Thesis-Master by Coursework |
author |
Shi, Mengqi |
author_sort |
Shi, Mengqi |
title |
Adversarial cross-modal unsupervised domain adaptation in semantic segmentation |
title_short |
Adversarial cross-modal unsupervised domain adaptation in semantic segmentation |
title_full |
Adversarial cross-modal unsupervised domain adaptation in semantic segmentation |
title_fullStr |
Adversarial cross-modal unsupervised domain adaptation in semantic segmentation |
title_full_unstemmed |
Adversarial cross-modal unsupervised domain adaptation in semantic segmentation |
title_sort |
adversarial cross-modal unsupervised domain adaptation in semantic segmentation |
publisher |
Nanyang Technological University |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/159248 |
_version_ |
1772827189402664960 |