Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation
Wang, Zhonghao
Content Files
WANG-THESIS-2019.pdf
Loading…
Download Files
Loading…
Download Counts (All Files)
Loading…
Edit File
Loading…
Permalink
https://hdl.handle.net/2142/106457
Description
Title
Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation
Author(s)
Wang, Zhonghao
Issue Date
2019-11-22
Director of Research (if dissertation) or Advisor (if thesis)
Huang, Thomas S.
Shi, Honghui
Department of Study
Electrical & Computer Eng
Discipline
Electrical & Computer Engr
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Date of Ingest
2020-03-02T22:38:46Z
Keyword(s)
domain adaptation
semantic segmentation
Abstract
We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. State-of-the-art approaches prove that performing semantic-level alignment is helpful in tackling the domain shift issue. Based on the observation that stuff categories usually share similar appearances across images of different domains while things (i.e. object instances) have much larger differences, we propose to improve the semantic-level alignment with different strategies for stuff regions and for things: (1) for the stuff categories, we generate the feature representation for each class and conduct the alignment operation from the target domain to the source domain; (2) for the thing categories, we generate the feature representation for each individual instance and encourage the instance in the target domain to align with the most similar one in the source domain. In this way, the individual differences within thing categories will also be considered to alleviate over-alignment. In addition to our proposed method, we further reveal the reason why the current adversarial loss is often unstable in minimizing the distribution discrepancy and show that our method can help ease this issue by minimizing the most similar stuff and instance features between the source and the target domains. We conduct extensive experiments in two unsupervised domain adaptation tasks, GTA5 to Cityscapes and SYNTHIA to Cityscapes, and achieve the new state-of-the-art segmentation accuracy.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
WANG-THESIS-2019.pdf
