Feature transfer based adversarial domain adaptation method for cross-domain road extraction

Abstract

In order to improve the cross-domain applicability of road segmentation, a feature transfer based adversarial domain adaptation method is presented for cross-domain road extraction. The presented method consists of two main parts, a feature transfer network and an adversarial domain adaption network. The feature transfer network transforms the images of the source domain into the feature space of the target domain. The adversarial domain adaption network learns to distinguish whether the results come from source domain or target domain, to promote the backbone network of road extraction to learn the common features of the road. The experimental results showed that the proposed method improved the generalization ability of the road extraction network and could extract the road target from cross-domain images accurately and effectively. The proposed method can realize the road extraction across domain without any annotation of target domain, so it has good application value.

Keywords:

• Road extraction
• transfer learning
• domain adaption
• generative adversarial network
• encoder-decoder network

Acknowledgements

The authors would like to thank Dragos Costea and Marius Leordeanu, for providing the Two City Dataset used in the experiments.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This research was supported by the National Natural Science Foundation of China (Grant No. 61673017, 61403398).