Lightweight temporal self-Attention for classifying satellite images time series

Vivien Sainte Fare Garnot (1) , Loic Landrieu (1)

1 LaSTIG - Laboratoire sciences et technologies de l'information géographique

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. 2020. 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 outper-forms 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.

Domaines: Machine Learning [stat.ML]; Réseau de neurones [cs.NE]; Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Vivien Sainte Fare Garnot, Loic Landrieu. Lightweight temporal self-Attention for classifying satellite images time series. Workshop on Advanced Analytics and Learning on Temporal Data, Sep 2020, en ligne, Belgium. ⟨hal-03016094⟩