Abstract
Recently, many segmentation methods based on supervised deep learning have been widely used in remote sensing images. However, these approaches often require a large number of labeled samples, which is difficult to obtain them for remote sensing images. Self-supervision is a new learning paradigm, and can solve the problem of lack of labeled samples. In this method, a large number of unlabeled samples are employed for pre-training, and then a few of labeled samples are leveraged for downstream tasks. Contrast learning is a typical self-supervised learning method. Inspired, we propose a Dense Multi-scale Feature Contrastive Learning Network (DMF-CLNet), which is divided into global and local feature extraction parts. Firstly, in the global part, instead of traditional ASPP, DenseASPP can obtain more context information of remote sensing images in a dense way without increasing parameters. Secondly, in the global and local parts, Coordinate Attention (CA) modules are introduced respectively to improve the overall performance of the segmentation model. Thirdly, in the global and local parts, the perceptual loss is calculated to extract deeper features. Two remote sensing image segmentation datasets are evaluated. The experimental results show that our model is superior to the current self-supervised contrastive learning methods and ImageNet pre-training techniques.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, J., Feng, L., Yao, F.: Improved maize cultivated area estimation over a large scale combining MODIS–EVI time series data and crop phenological information. ISPRS J. Photogramm. Remote Sens. 94, 102–113 (2014)
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49
Sargent, I., Zhang, C., Atkinson, P.M.: Joint deep learning for land cover and land use classification (2020). https://doi.org/10.17635/Lancaster/thesis/42
Sulla-Menashe, D., Gray, J.M., Abercrombie, S.P., Friedl, M.A.: Hierarchical mapping of annual global land cover 2001 to present: the MODIS collection 6 land cover product. Remote Sens. Environ. 222, 183–194 (2019)
Nan, L., Hong, H., Tao, F.: A novel texture-preceded segmentation algorithm for high-resolution imagery. IEEE Trans. Geosc. Remote Sens. 48(7), 2818–2828 (2010)
Huang, X., Zhang, L.: An SVM ensemble approach combining spectral, structural, and semantic features for the classification of high-resolution remotely sensed imagery. IEEE Trans. Geosci. Remote Sens. 51(1), 257–272 (2013)
Du, S., Zhang, F., Zhang, X.: Semantic classification of urban buildings combining VHR image and GIS data: an improved random forest approach. ISPRS J. Photogramm. Remote Sens. 105, 107–119 (2015)
Li, Z., Duan, W.: Classification of hyperspectral image based on double-branch dual-attention mechanism network. Remote Sens. 12(3), 582 (2020)
Alom, M.Z., Taha, T.M., Yakopcic, C., Westberg, S., Asari, V.K.: The history began from AlexNet: a comprehensive survey on deep learning approaches (2018)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019). https://doi.org/10.1186/s40537-019-0197-0
Supervised, S., Welling, B.M., Zemel, R.S.: Self Supervised (2008)
Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2020)
Li, H., et al.: Global and local contrastive self-supervised learning for semantic segmentation of HR remote sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1–14 (2022)
Yang, M., Yu, K., Chi, Z., Li, Z., Yang, K.: DenseASPP for semantic segmentation in street scenes CVPR (2018)
Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design (2021)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_43
Frid-Adar, M., Ben-Cohen, A., Amer, R., Greenspan, H.: Improving the segmentation of anatomical structures in chest radiographs using U-Net with an ImageNet pre-trained encoder. arXiv (2018)
Ma, X., Li, R., Lu, Z., Wei, W.: Mining constraints in role-based access control. Math. Comput. Model. 55(1–2), 87–96 (2012)
Jie, H., Li, S., Gang, S., Albanie, S.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. PP(99) (2012)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Hu, Z., Xu, M., Bai, S., Huang, T., Bai, X.: Asymmetric non-local neural networks for semantic segmentation. IEEE (2019)
Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: non-local networks meet squeeze-excitation networks and beyond. arXiv (2019)
Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. IEEE (2020)
Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: criss-cross attention for semantic segmentation. In: International Conference on Computer Vision (2018)
Fw, A., Fi, D.B.: Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network. Remote Sens. Environ. 245, 111741 (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations (2020)
Ding, L., Zhang, J., Bruzzone, L.: Semantic segmentation of large-size VHR remote sensing images using a two-stage multiscale training architecture. IEEE Trans. Geosci. Remote Sens. PP(99), 1–10 (2020)
Demir, I., Koperski, K., Lindenbaum, D., Pang, G., Huang, J., Basu, S.: DeepGlobe 2018: a challenge to parse the earth through satellite images. IEEE (2018)
Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. IEEE Computer Society (2015)
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Acknowledgement
This research was supported by the National Natural Science Foundation of China (No. 61901537), Research Funds for Overseas Students in Henan Province, China Postdoctoral Science Foundation (No. 2020M672274), Science and Technology Guiding Project of China National Textile and Apparel Council (No. 2019059), Postdoctoral Research Sponsorship in Henan Province (No. 19030018), Program of Young backbone teachers in Zhongyuan University of Technology (No. 2019XQG04), Training Program of Young Master's Supervisor in Zhongyuan University of Technology (No. SD202207).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Song, M., Li, B., Wei, P., Shao, Z., Wang, J., Huang, J. (2022). DMF-CL: Dense Multi-scale Feature Contrastive Learning for Semantic Segmentation of Remote-Sensing Images. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13537. Springer, Cham. https://doi.org/10.1007/978-3-031-18916-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-18916-6_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18915-9
Online ISBN: 978-3-031-18916-6
eBook Packages: Computer ScienceComputer Science (R0)