Multiresolution Convolutional Autoencoders
This work addresses the challenge of efficiently processing multiscale data in domains like spatial-temporal analysis, though it appears incremental as it combines existing techniques.
The authors tackled the problem of modeling multiscale spatio-temporal data by proposing a multi-resolution convolutional autoencoder (MrCAE) that adaptively integrates multigrid methods, convolutional autoencoders, and transfer learning, resulting in a network that progressively deepens and widens to capture scaled features dynamically.
We propose a multi-resolution convolutional autoencoder (MrCAE) architecture that integrates and leverages three highly successful mathematical architectures: (i) multigrid methods, (ii) convolutional autoencoders and (iii) transfer learning. The method provides an adaptive, hierarchical architecture that capitalizes on a progressive training approach for multiscale spatio-temporal data. This framework allows for inputs across multiple scales: starting from a compact (small number of weights) network architecture and low-resolution data, our network progressively deepens and widens itself in a principled manner to encode new information in the higher resolution data based on its current performance of reconstruction. Basic transfer learning techniques are applied to ensure information learned from previous training steps can be rapidly transferred to the larger network. As a result, the network can dynamically capture different scaled features at different depths of the network. The performance gains of this adaptive multiscale architecture are illustrated through a sequence of numerical experiments on synthetic examples and real-world spatial-temporal data.