ResiDualGAN: Resize-Residual DualGAN for Cross-Domain Remote Sensing Images Semantic Segmentation
-
Published:2023-03-03
Issue:5
Volume:15
Page:1428
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Zhao Yang12ORCID, Guo Peng12ORCID, Sun Zihao12ORCID, Chen Xiuwan12, Gao Han12ORCID
Affiliation:
1. Institute of Remote Sensing and Geographic Information System, Peking University, Beijing 100871, China 2. Deyang Institute of Smart Agriculture (DISA), TaiShan North Road 290, Deyang 618099, China
Abstract
The performance of a semantic segmentation model for remote sensing (RS) images pre-trained on an annotated dataset greatly decreases when testing on another unannotated dataset because of the domain gap. Adversarial generative methods, e.g., DualGAN, are utilized for unpaired image-to-image translation to minimize the pixel-level domain gap, which is one of the common approaches for unsupervised domain adaptation (UDA). However, the existing image translation methods face two problems when performing RS image translation: (1) ignoring the scale discrepancy between two RS datasets, which greatly affects the accuracy performance of scale-invariant objects; (2) ignoring the characteristic of real-to-real translation of RS images, which brings an unstable factor for the training of the models. In this paper, ResiDualGAN is proposed for RS image translation, where an in-network resizer module is used for addressing the scale discrepancy of RS datasets and a residual connection is used for strengthening the stability of real-to-real images translation and improving the performance in cross-domain semantic segmentation tasks. Combined with an output space adaptation method, the proposed method greatly improves the accuracy performance on common benchmarks, which demonstrates the superiority and reliability of ResiDualGAN. At the end of the paper, a thorough discussion is conducted to provide a reasonable explanation for the improvement of ResiDualGAN. Our source code is also available.
Funder
Integovernmental cooperation in international science and technology innovation of the Ministry of Science and Technology
Subject
General Earth and Planetary Sciences
Reference53 articles.
1. Gao, H., Guo, J., Guo, P., and Chen, X. (2021). Classification of Very-High-Spatial-Resolution Aerial Images Based on Multiscale Features with Limited Semantic Information. Remote Sens., 13. 2. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–8). ImageNet Classification with Deep Convolutional Neural Networks. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA. 3. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA. 4. Ronneberger, O., Fischer, P., and Brox, T. (2015). Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer. 5. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8–14). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|