Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
From MaRDI portal
Publication:69123
DOI10.48550/ARXIV.2007.00586arXiv2007.00586MaRDI QIDQ69123FDOQ69123
Authors: Vivien Sainte Fare Garnot, Loic Landrieu 
Publication date: 1 July 2020
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. 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.
Cited In (1)
This page was built for publication: Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q69123)
