Sensing and Imaging

, 19:6 | Cite as

Transfer Learning for Classification of Optical Satellite Image

Original Paper
  • 11 Downloads
Part of the following topical collections:
  1. Recent Developments in Sensing and Imaging

Abstract

Deep convolutional neural network (DCNN) has achieved great success in the classification of natural images, but it requires numerous labelled data for training. In the absence of a large number of optical satellite images and labelled data, how to guarantee the effect of classification of the optical satellite images with DCNN? In this case, this paper has discussed how to fine-tune a pre-trained DCNN in a layer-wise manner by transfer learning. In our experiment, DCNN is pre-trained with ImageNet which is a large labelled dataset of natural images, and then optical remote sensing images are used to fine-tune the learnable parameters of pre-trained DCNN. The experimental results show that transfer learning is feasible to deal with the above problem. In the process of transfer training, if the second half of the layers are fine-tuned, compared with the fine-tuning of the entire network, the almost same accuracy can be achieved, but the convergence is more rapid. The experimental results provide a solution for how to achieve the incremental classification performance in practical applications.

Keywords

Optical remote sensing image Deep convolutional neural network Classification Transfer learning Fine-tuning 

References

  1. 1.
    Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In NIPS’12 Proceedings of the 25th international conference on neural information processing systems, Lake Tahoe, Nevada December 03–06, 2012, (Vol. 1, pp. 1097–1105).Google Scholar
  2. 2.
    Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural Computation, 29(9), 2352–2449.  https://doi.org/10.1162/NECO_a_00990.CrossRefGoogle Scholar
  3. 3.
    Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, Massachusetts June 08–10, 2015 (pp. 3431–3440).  https://doi.org/10.1109/CVPR.2015.7298965
  4. 4.
    Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, Montreal, Canada December 07–12, 2015 (pp. 91–99).Google Scholar
  5. 5.
    Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks?. Montreal, Canada December 08 - 13, 2014, In Advances in neural information processing systems (Vol. 27, pp. 3320–3328).Google Scholar
  6. 6.
    Long, M., Cao, Y., Wang, J., & Jordan, M. (2015). Learning transferable features with deep adaptation networks. In Proceedings of the 32nd international conference on machine learning, Lille, France July 06–11, 2015 (Vol. 37, pp. 97–105).Google Scholar
  7. 7.
    Sun, X., Fu, K., Long, H., Hu, Y., Cai, L., & Wang, H. (2008, July). Contextual models for automatic building extraction in high resolution remote sensing image using object-based boosting method. In Geoscience and remote sensing symposium, 2008. IGARSS 2008. IEEE International (Vol. 2, pp. II-437). IEEE.  https://doi.org/10.1109/IGARSS.2008.4779022
  8. 8.
    Qu, J. S., Qu, S. B., & Wang, Z. J. (2009). Feature-based fuzzy-neural network approach for target classification and recognition in remote sensing images. Journal of Remote Sensing, 13(1), 68–74.Google Scholar
  9. 9.
    Zhao, C., & Qi, B. (2012). Hyperspectral image classification based on fuzzy kernel weighted c-means clustering. Chinese Journal of Scientific Instrument, 33(9), 2016–2021.Google Scholar
  10. 10.
    Zhu, C., Zhou, H., Wang, R., & Guo, J. (2010). A novel hierarchical method of ship detection from spaceborne optical image based on shape and texture features. IEEE Transactions on geoscience and remote sensing, 48(9), 3446–3456.  https://doi.org/10.1109/TGRS.2010.2046330.CrossRefGoogle Scholar
  11. 11.
    Chen, S., Wang, H., Xu, F., & Jin, Y. Q. (2016). Target classification using the deep convolutional networks for SAR images. IEEE Transactions on Geoscience and Remote Sensing, 54(8), 4806–4817.  https://doi.org/10.1109/TGRS.2016.2551720.CrossRefGoogle Scholar
  12. 12.
    Luus, F. P., Salmon, B. P., van den Bergh, F., & Maharaj, B. T. J. (2015). Multiview deep learning for land-use classification. IEEE Geoscience and Remote Sensing Letters, 12(12), 2448–2452.  https://doi.org/10.1109/LGRS.2015.2483680.CrossRefGoogle Scholar
  13. 13.
    Zhou, Y., Wang, H., Xu, F., & Jin, Y. Q. (2016). Polarimetric SAR image classification using deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 13(12), 1935–1939.  https://doi.org/10.1109/LGRS.2016.2618840.CrossRefGoogle Scholar
  14. 14.
    Chen, X., Xiang, S., Liu, C. L., & Pan, C. H. (2014). Vehicle detection in satellite images by hybrid deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 11(10), 1797–1801.  https://doi.org/10.1109/LGRS.2014.2309695.CrossRefGoogle Scholar
  15. 15.
    Tang, J., Deng, C., Huang, G. B., & Zhao, B. (2015). Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine. IEEE Transactions on Geoscience and Remote Sensing, 53(3), 1174–1185.  https://doi.org/10.1109/TGRS.2014.2335751.CrossRefGoogle Scholar
  16. 16.
    Yu, D., Wang, H., Chen, P., & Wei, Z. (2014). Mixed pooling for convolutional neural networks. In the 9th international conference on rough sets and knowledge technology (RSKT’14), Shanghai, China October 24–26, 2014 (pp. 364–375). Springer, Cham.  https://doi.org/10.1007/978-3-319-11740-9_34
  17. 17.
    He, J., Zou, M., & Liu, P. (2017). Convolutional neural networks for chinese sentiment classification of social network. In 2017 IEEE international conference on mechatronics and automation (ICMA), Takamatsu, Japan August 06-09, (pp. 1877–1881). IEEE.  https://doi.org/10.1109/ICMA.2017.8016104
  18. 18.
    Nair, V., & Hinton, G. E. (2010). Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10), Haifa, Israel June 21–24, 2010 (pp. 807–814).Google Scholar
  19. 19.
    Konecny, J., Liu, J., Richtarik, P., & Takac, M. (2016). Mini-batch semi-stochastic gradient descent in the proximal setting. IEEE Journal of Selected Topics in Signal Processing, 10(2), 242–255.CrossRefGoogle Scholar
  20. 20.
    Zhuang, F. Z., LUO, P., HE, Q., & Shi, Z. (2015). Survey on transfer learning research. Journal of Software, 26(1), 26–39.MathSciNetGoogle Scholar
  21. 21.
    Fengmei, W., Jianpei, Z., Yan, C., & Jing, Y. (2014). FSFP: Transfer learning from long texts to the short. Applied Mathematics & Information Sciences, 8(4), 2033.  https://doi.org/10.12785/amis/080462.CrossRefGoogle Scholar
  22. 22.
    Dai, W., Xue, G. R., Yang, Q., & Yu, Y. (2007). Co-clustering based classification for out-of-domain documents. In Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, California, USA August 12–15, 2007 (pp. 210-219). ACM.  https://doi.org/10.1145/1281192.1281218
  23. 23.
    Samanta, S., Selvan, A. T., & Das, S. (2013). Cross-Domain clustering performed by transfer of knowledge across domains. In 2013 Fourth International conference on computer vision, pattern recognition, image processing and graphics (NCVPRIPG), Jodhpur, India December 18–21, 2013 (pp. 1–4). IEEE.  https://doi.org/10.1109/NCVPRIPG.2013.6776213
  24. 24.
    Dai, W., Yang, Q., Xue, G. R., & Yu, Y. (2008, July). Self-taught clustering. In Proceedings of the 25th international conference on machine learning, Helsinki, Finland July 05–09, 2008 (pp. 200–207). ACM.  https://doi.org/10.1145/1390156.1390182
  25. 25.
    Sharif Razavian, A., Azizpour, H., Sullivan, J., & Carlsson, S. (2014). CNN features off-the-shelf: an astounding baseline for recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, Columbus, Ohio June 23–28, 2014 (pp. 806–813).  https://doi.org/10.1109/CVPRW.2014.131
  26. 26.
    Penatti, O. A., Nogueira, K., & dos Santos, J. A. (2015). Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, Boston, Massachusetts June 11–12,2015 (pp. 44–51).Google Scholar
  27. 27.
    Maggiori, E., Tarabalka, Y., Charpiat, G., & Alliez, P. (2017). Convolutional neural networks for large-scale remote-sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 55(2), 645–657.  https://doi.org/10.1109/TGRS.2016.2612821.CrossRefGoogle Scholar
  28. 28.
    Azizpour, H., Sharif Razavian, A., Sullivan, J., Maki, A., & Carlsson, S. (2015). From generic to specific deep representations for visual recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, Boston, Massachusetts June 11–12,2015 (pp. 36–45).  https://doi.org/10.1109/CVPRW.2015.7301270
  29. 29.
    Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2014). Decaf: A deep convolutional activation feature for generic visual recognition. In Proceedings of the 31st international conference on machine learning, Beijing, China June 21C26, 2014 (Vol. 32, pp. 647–655).Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Chengdu Institute of Computer ApplicationUniversity of Chinese Academy of SciencesChengduChina
  2. 2.Chengdu University of Information TechnologyChengduChina

Personalised recommendations