Super-Resolution of Large Volumes of Sentinel-2 Images with High Performance Distributed Deep Learning
| Autor: | Run Zhang, Jenia Jitsev, Gabriele Cavallaro |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Speedup
010504 meteorology & atmospheric sciences Data parallelism business.industry Computer science Deep learning 0211 other engineering and technologies 02 engineering and technology Supercomputer Residual 01 natural sciences Data modeling Computer engineering ddc:610 Artificial intelligence business Throughput (business) Image resolution 021101 geological & geomatics engineering 0105 earth and related environmental sciences |
| Zdroj: | IGARSS 617-620 (2020). doi:10.1109/IGARSS39084.2020.9323734 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020, Online event, Hawaii, 2020-09-26-2020-10-02 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Online event, Online event, 2020-09-26-2020-10-02 |
| Popis: | This work proposes a novel distributed deep learning model for Remote Sensing (RS) images super-resolution. High Performance Computing (HPC) systems with GPUs are used to accelerate the learning of the unknown low to high resolution mapping from large volumes of Sentinel-2 data. The proposed deep learning model is based on self-attention mechanism and residual learning. The results demonstrate that stateof- the-art performance can be achieved by keeping the size of the model relatively small. Synchronous data parallelism is applied to scale up the training process without severe performance loss. Distributed training is thus shown to speed up learning substantially while keeping performance intact. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|