Home > Archive > 2020 > Volume 10 Number 5 (Sept. 2020) >
IJMLC 2020 Vol.10(5): 648-653 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2020.10.5.986

An Adversarial Self-Learning Method for Cross-City Adaptation in Semantic Segmentation

Huachen Yu and Jianming Yang

Abstract—Semantic segmentation is an important task in the visual system of self-driving cars. The semantic segmentation models based on the CNN (Convolutional Neural Network) trained with the large numbers of annotated labels may not work well at the environments different from the training sets due to the domain gap between the train and test domains. Just for the reduction of the distance between the source and target domains, domain adaptation methods are proposed for the unsupervised training with the unlabeled target domain. Not only the reduction of the domain-shift, but we also propose the self-learning method to enhance the predicted probabilities of the target domain. To gain more accurate probability maps of the target domain generated from the segmentation model which is trained by the source domain, we propose the adversarial self-learning method which is consists of the domain adaptation part and self-learning part. The adversarial self-learning method can maximize the predicted probabilities for the probability maps of the target domain gained from the segmentation model which is adapted with the domain adaptation method before the self-learning. With the Cityscapes to NTHU cross-city adaptation experiments, we can see that the adversarial self-learning method can achieve stateof- the-art results compared with the domain adaptation methods proposed in the recent researches.

Index Terms—Semantic segmentation, domain adaptation, adversarial self-learning, cross-city adaptation.

Huachen Yu and Jianming Yang are with the Department of Mechanical Engineering, Meijo University, Nagoya, Japan (e-mail: huachen_yu@yahoo.com, yang@meijo-u.ac.jp).


Cite: Huachen Yu and Jianming Yang, "An Adversarial Self-Learning Method for Cross-City Adaptation in Semantic Segmentation," International Journal of Machine Learning and Computing vol. 10, no. 5, pp. 648-653, 2020.

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

General Information

  • ISSN: 2010-3700 (Online)
  • Abbreviated Title: Int. J. Mach. Learn. Comput.
  • Frequency: Bimonthly
  • DOI: 10.18178/IJMLC
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals Library.
  • E-mail: ijmlc@ejournal.net

Article Metrics