Towards Conceptual Compression
This addresses a fundamental problem in unsupervised learning for computer vision by improving image modeling and compression.
The paper tackles image modeling by introducing a recurrent variational auto-encoder that achieves state-of-the-art results on ImageNet and Omniglot datasets, enabling high-quality conceptual compression by separating global conceptual information from lower-level details.
We introduce a simple recurrent variational auto-encoder architecture that significantly improves image modeling. The system represents the state-of-the-art in latent variable models for both the ImageNet and Omniglot datasets. We show that it naturally separates global conceptual information from lower level details, thus addressing one of the fundamentally desired properties of unsupervised learning. Furthermore, the possibility of restricting ourselves to storing only global information about an image allows us to achieve high quality 'conceptual compression'.