Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
This incremental improvement addresses the need for scalable processing of Earth observation data for industrial and state actors.
The authors tackled the problem of efficiently classifying satellite image time series by proposing a lightweight modification of the Temporal Attention Encoder, which outperforms state-of-the-art methods with fewer parameters and reduced computational complexity.
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. 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.