Published July 3, 2020 | Version 1.0
Other Open

Lightweight Temporal Attention Encoder - Pre-trained weights

  • 1. LASTIG IGN ENSG, Univ. Gustave Eiffel

Description

Pre-trained weights for the Pixel-Set Encoder + Lightweight Temporal Attention Encoder architecture for agricultural parcel classification on Sentinel-2 satellite image time series.

This architecture is presented in the following paper:

Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
https://arxiv.org/abs/2007.00586

The PyTorch code associated is located in the following github repository:
https://github.com/VSainteuf/lightweight-temporal-attention-pytorch

Files

PSE-LTAE-pre-trained-weights.zip

Files (8.1 MB)

Name Size Download all
md5:8c89c6c606d58c061fdef5d3458f2a6e
8.1 MB Preview Download