Abstract
Recently, convolution neural network based methods have dominated the remote sensing image super-resolution (RSISR). However, most of them own complex network structures and a large number of network parameters, which is not friendly to computational resources limited scenarios. Besides, scale variations of objects in the remote sensing image are still challenging for most methods to generate high-quality super-resolution results. To this end, we propose a scale-aware group convolution (SGC) for RSISR. Specifically, each SGC firstly uses group convolutions with different dilation rates for extracting multi-scale features. Then, a scale-aware feature guidance approach and enhancement approach are leveraged to enhance the representation ability of different scale features. Based on SGC, a cascaded scale-aware distillation network (CSDN) is designed, which is composed of multiple SGC based cascade scale-aware distillation blocks (CSDBs). The output of each CSDB will be fused via the backward feature fusion module for final image super-resolution reconstruction. Extensive experiments are performed on the commonly-used UC Merced dataset. Quantitative and qualitative experiment results demonstrate the effectiveness of our method.
This work is supported by the Natural Science Foundation of Hebei Province (F2019201451).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Latif, Z.A., Zaqwan, H.M., Saufi, M., Adnan, N.A., Omar, H.: Deforestation and carbon loss estimation at tropical forest using multispectral remote sensing: case study of Besul Tambahan permanent forest reserve. In: IconSpace, pp. 348–351 (2015)
Ahn, N., Kang, B., Sohn, K.A.: Fast, accurate, and lightweight super-resolution with cascading residual network. In: ECCV, pp. 252–268 (2018)
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: ECCV, pp. 184–199 (2014)
Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: ECCV, pp. 391–407 (2016)
Dong, X., Wang, L., Sun, X., Jia, X., Gao, L., Zhang, B.: Remote sensing image super-resolution using second-order multi-scale networks. IEEE T-GRS 59(4), 3473–3485 (2020)
Haut, J.M., Fernandez-Beltran, R., Paoletti, M.E., Plaza, J., Plaza, A., Pla, F.: A new deep generative network for unsupervised remote sensing single-image super-resolution. IEEE T-GRS 56(11), 6792–6810 (2018)
Haut, J.M., Paoletti, M.E., Fernández-Beltran, R., Plaza, J., Plaza, A., Li, J.: Remote sensing single-image superresolution based on a deep compendium model. IEEE GRSL 16(9), 1432–1436 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132–7141 (2018)
Huan, H., et al.: End-to-end super-resolution for remote-sensing images using an improved multi-scale residual network. Remote Sens. 13(4), 666 (2021)
Hui, Z., Gao, X., Yang, Y., Wang, X.: Lightweight image super-resolution with information multi-distillation network. In: ACM MM, pp. 2024–2032 (2019)
Kim, J., Lee, J.K., Lee, K.M.: Deeply-recursive convolutional network for image super-resolution. In: CVPR, pp. 1637–1645 (2016)
Lei, S., Shi, Z.: Hybrid-scale self-similarity exploitation for remote sensing image super-resolution. IEEE T-GRS 60, 1–10 (2021)
Lei, S., Shi, Z., Zou, Z.: Super-resolution for remote sensing images via local-global combined network. IEEE GRSL 14(8), 1243–1247 (2017)
Li, D., Liu, J., Zhou, Q., Wang, L., Huang, Q.: Study on information extraction of rape acreage based on TM remote sensing image. In: IGARSS, pp. 3323–3326 (2011)
Li, X., Zhou, T., Li, J., Zhou, Y., Zhang, Z.: Group-wise semantic mining for weakly supervised semantic segmentation. In: AAAI, vol. 35, pp. 1984–1992 (2021)
Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
Liu, J., Tang, J., Wu, G.: Residual feature distillation network for lightweight image super-resolution. In: ECCV, pp. 41–55 (2020)
Lu, H., Lu, Y., Li, G., Sun, Y., Wang, S., Li, Y.: Scale-aware distillation network for lightweight image super-resolution. In: PRCV, pp. 128–139 (2021)
Luo, X., Xie, Y., Zhang, Y., Qu, Y., Li, C., Fu, Y.: LatticeNet: towards lightweight image super-resolution with lattice block. In: ECCV, pp. 272–289 (2020)
Mei, Y., Fan, Y., Zhou, Y., Huang, L., Huang, T.S., Shi, H.: Image super-resolution with cross-scale non-local attention and exhaustive self-exemplars mining. In: CVPR, pp. 5690–5699 (2020)
Pan, Z., Ma, W., Guo, J., Lei, B.: Super-resolution of single remote sensing image based on residual dense backprojection networks. IEEE T-GRS 57(10), 7918–7933 (2019)
Tang, Z., Chen, Q., Wang, X.: Meteorological observation station’s environment identification base on remote sensing image. In: AIMSEC, pp. 4056–4060 (2011)
Wang, S., Zhou, T., Lu, Y., Di, H.: Detail preserving transformer for light field image super-resolution. In: AAAI, vol. 36, pp. 2522–2530 (2022)
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794–7803 (2018)
Wang, X., Wu, Y., Ming, Y., Lv, H.: Remote sensing imagery super resolution based on adaptive multi-scale feature fusion network. Sensors 20(4), 1142 (2020)
Wang, Y., Lu, Y., Wang, S., Zhang, W., Wang, Z.: Local-global feature aggregation for light field image super-resolution. In: ICASSP, pp. 2160–2164 (2022)
Wang, Z., Lu, Y., Li, W., Wang, S., Wang, X., Chen, X.: Single image super-resolution with attention-based densely connected module. Neurocomputing 453, 876–884 (2021)
Xu, W., Xu, G., Wang, Y., Sun, X., Lin, D., Wu, Y.: Deep memory connected neural network for optical remote sensing image restoration. Remote Sens. 10(12), 1893 (2018)
Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE TIP 19(11), 2861–2873 (2010)
Yang, Y., Newsam, S.: Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 270–279 (2010)
Zhou, T., Li, J., Wang, S., Tao, R., Shen, J.: MATNet: motion-attentive transition network for zero-shot video object segmentation. IEEE TIP 29, 8326–8338 (2020)
Zhou, T., Li, L., Li, X., Feng, C.M., Li, J., Shao, L.: Group-wise learning for weakly supervised semantic segmentation. IEEE TIP 31, 799–811 (2021)
Zhou, T., Qi, S., Wang, W., Shen, J., Zhu, S.C.: Cascaded parsing of human-object interaction recognition 44(6), 2827–2840 (2021)
Zhou, T., Wang, S., Zhou, Y., Yao, Y., Li, J., Shao, L.: Motion-attentive transition for zero-shot video object segmentation. In: AAAI, vol. 34, pp. 13066–13073 (2020)
Zhou, T., Wang, W., Qi, S., Ling, H., Shen, J.: Cascaded human-object interaction recognition. In: CVPR, pp. 4263–4272 (2020)
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
Ji, H., Di, H., Wang, S., Shi, Q. (2022). Cascade Scale-Aware Distillation Network for Lightweight Remote Sensing Image Super-Resolution. 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_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-18916-6_23
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)