Mutual information maximization provides an appealing formalism for learning representations of data.
Meta-reinforcement learning algorithms can enable autonomous agents, such as robots, to quickly acquire new behaviors by leveraging prior experience in a set of related training tasks.
In our approach, we perform online probabilistic filtering of latent task variables to infer how to solve a new task from small amounts of experience.
Learning-based methods for visual segmentation have made progress on particular types of segmentation tasks, but are limited by the necessary supervision, the narrow definitions of fixed tasks, and the lack of control during inference for correcting errors.
Recent years have seen tremendous progress in still-image segmentation; however the na\"ive application of these state-of-the-art algorithms to every video frame requires considerable computation and ignores the temporal continuity inherent in video.
4) A new method for discovering and displaying the visual elements used by the CNN-based date-prediction model to date portraits, finding that they correspond to the tell-tale fashions of each era.