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).