Communication Dans Un Congrès Année : 2020

Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention

Résumé

Satellite image time series, bolstered by their growing availability , are at the forefront of an extensive effort towards automated Earth monitoring by international institutions. In particular, large-scale control of agricultural parcels is an issue of major political and economic importance. In this regard, hybrid convolutional-recurrent neural architectures have shown promising results for the automated classification of satellite image time series.We propose an alternative approach in which the convolutional layers are advantageously replaced with encoders operating on unordered sets of pixels to exploit the typically coarse resolution of publicly available satellite images. We also propose to extract temporal features using a bespoke neural architecture based on self-attention instead of recurrent networks. We demonstrate experimentally that our method not only out-performs previous state-of-the-art approaches in terms of precision, but also significantly decreases processing time and memory requirements. Lastly, we release a large open-access annotated dataset as a benchmark for future work on satellite image time series.

Fichier principal
Vignette du fichier
1911.07757(4).pdf (3.5 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-02879223 , version 1 (23-06-2020)

Licence

Identifiants

  • HAL Id : hal-02879223 , version 1

Citer

Vivien Sainte Fare Garnot, Loic Landrieu, Sebastien Giordano, Nesrine Chehata. Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention. CVPR 2020, Jun 2020, Seattle, United States. ⟨hal-02879223⟩
199 Consultations
504 Téléchargements

Partager

  • More