AI Technology & Industry Review
In a new paper Scaling Robot Learning with Semantically Imagined Experience, a team from Robotics at Google and Google Research Robot proposes Learning with Semantically Imagined Experience (ROSIE), a general and semantically-aware data augmentation strategy that leverages text-to-image models to obtain data for robot learning.
The new DeepMind paper Data Augmentation for Efficient Learning from Parametric Experts proposes Augmented Policy Cloning (APC), a simple yet effective data-augmentation approach designed to support data-efficient learning from parametric experts. The method significantly improves data efficiency across various control and reinforcement learning settings.
In the new paper Deep AutoAugment, a research team from Michigan State University and Amazon Web Services proposes Deep AutoAugment (DeepAA), a fully automated multi-layer data augmentation search method that eliminates the need for hand-crafted default transformations.
Researchers from Carnegie Mellon University and Google Brain have now proposed an unsupervised data augmentation (UDA) technique that significantly improves semi-supervised learning (SSL) by conducting data augmentation on unlabeled data.
Graham Taylor from the University of Guelph gave a talk at the University of Toronto, summarizing current techniques used to address the issue of insufficient labeled data.