Compressed sensing-based Magnetic Resonance Imaging (CS-MRI) is a promising paradigm allowing to accelerate MRI acquisition by reconstructing images from only a fraction of the normally required k-space measurements. Traditionally, sparsity-based methods and their data-driven variants such as dictionary learning [10] have been popular due to their mathematically robust formulation for perfect reconstruction. However, these methods are limited in acceleration factor and also suffer from high computational complexity. More recently, several deep learning-based architectures have been proposed as an attractive alternative for CS-MRI. The advantages of these techniques are their computational efficiency, G. Yang and J. Schlemper/D. Rueckert and A. Maier share second/last coauthorship.

No abstract

Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multiobject environments it is difficult to disentangle all the factors of variation into such a fixed-length representation of the whole scene. We propose to use object-centric representations as a modular and structured observation space, which is learned with a compositional generative world model. We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills. These skills can be further combined to address compositional tasks like the manipulation of several different objects.https://sites.google.com/view/smorl-iclr2021 * equal contribution