Abstract
The increasing accessibility and precision of Earth observation satellite data offers considerable opportunities for industrial and state actors alike. This calls however for efficient methods able to process time-series on a global scale. Building on recent work employing multi-headed self-attention mechanisms to classify remote sensing time sequences, we propose a modification of the Temporal Attention Encoder of Garnot et al. [5]. In our network, the channels of the temporal inputs are distributed among several compact attention heads operating in parallel. Each head extracts highly-specialized temporal features which are in turn concatenated into a single representation. Our approach outperforms other state-of-the-art time series classification algorithms on an open-access satellite image dataset, while using significantly fewer parameters and with a reduced computational complexity.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
E and H are typically powers of 2 and \(E>H\), ensuring that \(E'\) remains integer.
References
Bailly, A., Malinowski, S., Tavenard, R., Chapel, L., Guyet, T.: Dense bag-of-temporal-SIFT-words for time series classification. In: Douzal-Chouakria, A., Vilar, J.A., Marteau, P.-F. (eds.) AALTD 2015. LNCS (LNAI), vol. 9785, pp. 17–30. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44412-3_2
Bailly, S., Giordano, S., Landrieu, L., Chehata, N.: Crop-rotation structured classification using multi-source Sentinel images and LPIS for crop type mapping. In: IGARSS (2018)
Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR (2014)
Garnot, V.S.F., Landrieu, L., Giordano, S., Chehata, N.: Time-space tradeoff in deep learning models for crop classification on satellite multi-spectral image time series. In: IGARSS (2019)
Garnot, V.S.F., Landrieu, L., Giordano, S., Chehata, N.: Satellite image time series classification with pixel-set encoders and temporal self-attention. In: CVPR (2020)
Ji, S., Zhang, C., Xu, A., Shi, Y., Duan, Y.: 3D convolutional neural networks for crop classification with multi-temporal remote sensing images. Remote Sens. 10, 75 (2018)
Kussul, N., Lemoine, G., Gallego, F.J., Skakun, S.V., Lavreniuk, M., Shelestov, A.Y.: Parcel-based crop classification in Ukraine using Landsat-8 data and Sentinel-1A data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 9, 2500–2508 (2016)
Pelletier, C., Valero, S., Inglada, J., Champion, N., Dedieu, G.: Assessing the robustness of random forests to map land cover with high resolution satellite image time series over large areas. Remote Sens. Environ. 187, 156–168 (2016)
Pelletier, C., Webb, G.I., Petitjean, F.: Temporal convolutional neural network for the classification of satellite image time series. Remote Sens. 11, 523 (2019)
Rußwurm, M., Körner, M.: Convolutional LSTMs for cloud-robust segmentation of remote sensing imagery. In: NeurIPS Workshop (2018)
Rußwurm, M., Körner, M.: Self-attention for raw optical satellite time series classification. arXiv preprint arXiv:1910.10536 (2019)
Tavenard, R., Malinowski, S., Chapel, L., Bailly, A., Sanchez, H., Bustos, B.: Efficient temporal kernels between feature sets for time series classification. In: Ceci, M., Hollmén, J., Todorovski, L., Vens, C., Džeroski, S. (eds.) ECML PKDD 2017. LNCS (LNAI), vol. 10535, pp. 528–543. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71246-8_32
Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)
Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_1
Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.c.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. INeurIPS (2015)
Ye, L., Keogh, E.: Time series shapelets: a new primitive for data mining. In: ACM SIGKDD (2009)
Acknowledgments
This research was supported by the AI4GEO project: http://www.ai4geo.eu/ and the French Agriculture Paying Agency (ASP).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Garnot, V.S.F., Landrieu, L. (2020). Lightweight Temporal Self-attention for Classifying Satellite Images Time Series. In: Lemaire, V., Malinowski, S., Bagnall, A., Guyet, T., Tavenard, R., Ifrim, G. (eds) Advanced Analytics and Learning on Temporal Data. AALTD 2020. Lecture Notes in Computer Science(), vol 12588. Springer, Cham. https://doi.org/10.1007/978-3-030-65742-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-65742-0_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65741-3
Online ISBN: 978-3-030-65742-0
eBook Packages: Computer ScienceComputer Science (R0)
