Representation Learning for Remote Sensing: An Unsupervised Sensor Fusion Approach
arXiv:2108.05094
Abstract
In the application of machine learning to remote sensing, labeled data is often scarce or expensive, which impedes the training of powerful models like deep convolutional neural networks. Although unlabeled data is abundant, recent self-supervised learning approaches are ill-suited to the remote sensing domain. In addition, most remote sensing applications currently use only a small subset of the multi-sensor, multi-channel information available, motivating the need for fused multi-sensor representations. We propose a new self-supervised training objective, Contrastive Sensor Fusion, which exploits coterminous data from multiple sources to learn useful representations of every possible combination of those sources. This method uses information common across multiple sensors and bands by training a single model to produce a representation that remains similar when any subset of its input channels is used. Using a dataset of 47 million unlabeled coterminous image triplets, we train an encoder to produce semantically meaningful representations from any possible combination of channels from the input sensors. These representations outperform fully supervised ImageNet weights on a remote sensing classification task and improve as more sensors are fused. Our code is available at https://storage.cloud.google.com/public-published-datasets/csf_code.zip.
arXiv comment9 pages, 5 figures. Work completed in 2019 and submitted to ICLR in 2020. Source code available at: https://github.com/descarteslabs/contrastive_sensor_fusion. Data available at: https://storage.cloud.google.com/public-published-datasets/osm_example_dataset.zip?folder=true&organizationId=272688069953
References in corpus (9)
- Distributed Representations of Words and Phrases and their Compositionality
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Learning deep representations by mutual information estimation and maximization
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- Learning Representations by Maximizing Mutual Information Across Views
- Contrastive Multiview Coding
- Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
- A Deep and Tractable Density Estimator
- Visual search over billions of aerial and satellite images