Learning Disentangled Representations of Satellite Image Time Series
arXiv:1903.08863
Abstract
In this paper, we investigate how to learn a suitable representation of satellite image time series in an unsupervised manner by leveraging large amounts of unlabeled data. Additionally , we aim to disentangle the representation of time series into two representations: a shared representation that captures the common information between the images of a time series and an exclusive representation that contains the specific information of each image of the time series. To address these issues, we propose a model that combines a novel component called cross-domain autoencoders with the variational autoencoder (VAE) and generative ad-versarial network (GAN) methods. In order to learn disentangled representations of time series, our model learns the multimodal image-to-image translation task. We train our model using satellite image time series from the Sentinel-2 mission. Several experiments are carried out to evaluate the obtained representations. We show that these disentangled representations can be very useful to perform multiple tasks such as image classification, image retrieval, image segmentation and change detection.
References in corpus (16)
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Deep Residual Learning for Image Recognition
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Improved Training of Wasserstein GANs
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Adversarial Feature Learning
- Autoencoding beyond pixels using a learned similarity metric
- A note on the evaluation of generative models
- Multimodal Unsupervised Image-to-Image Translation
- Stochastic Adversarial Video Prediction
- Least Squares Generative Adversarial Networks
- Image-to-image translation for cross-domain disentanglement
- Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency