Remote Sensing Image Translation via Style-Based Recalibration Module and Improved Style Discriminator

Existing remote sensing change detection methods are heavily affected by seasonal variation. Since vegetation colors are different between winter and summer, such variations are inclined to be falsely detected as changes. In this letter, we proposed an image translation method to solve the problem. A style-based recalibration module is introduced to capture seasonal features effectively. Then, a new style discriminator is designed to improve the translation performance. The discriminator can not only produce a decision for the fake or real sample but also return a style vector according to the channel-wise correlations. Extensive experiments are conducted on the season-varying data set. The experimental results show that the proposed method can effectively perform image translation, thereby consistently improving the season-varying image change detection performance. Our codes and data are available at https://github.com/summitgao/RSIT_SRM_ISD.

[1]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[2]  Sudipan Saha,et al.  Building Change Detection in VHR SAR Images via Unsupervised Deep Transcoding , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Yuan Yuan,et al.  Pixel-Wise Crowd Understanding via Synthetic Data , 2020, International Journal of Computer Vision.

[4]  Hyo-Eun Kim,et al.  SRM: A Style-Based Recalibration Module for Convolutional Neural Networks , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[5]  Turgay Çelik,et al.  Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means Clustering , 2009, IEEE Geoscience and Remote Sensing Letters.

[6]  Minjae Kim,et al.  U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation , 2019, ICLR.

[7]  Lorenzo Bruzzone,et al.  Automatic analysis of the difference image for unsupervised change detection , 2000, IEEE Trans. Geosci. Remote. Sens..

[8]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[9]  Jan Kautz,et al.  Multimodal Unsupervised Image-to-Image Translation , 2018, ECCV.

[10]  Zhenghang Yuan,et al.  GETNET: A General End-to-end Two-dimensional CNN Framework for Hyperspectral Image Change Detection , 2019, ArXiv.

[11]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Yong Dou,et al.  Image Translation Between High-Resolution Remote Sensing Optical and SAR Data Using Conditional GAN , 2018, PCM.

[13]  Weiming Wang,et al.  Image Translation Between Sar and Optical Imagery with Generative Adversarial Nets , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[14]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[15]  Hasan F. Ates,et al.  Disaster Damage Assessment of Buildings Using Adaptive Self-Similarity Descriptor , 2016, IEEE Geoscience and Remote Sensing Letters.

[16]  Arthur Gretton,et al.  Demystifying MMD GANs , 2018, ICLR.

[17]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .