Metalearning Websites
Mid-Level Visual Features Improve Generalization and Sample Efficienct
Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks. UC Berkeley, FAIR, Stanford. A large-scale study of how to use pretrained perception networks for performing active tasks..
Not Applicable
$
8.95
Taskonomy
Taskonomy: Disentangling Task Transfer Learning, CVPR 2018 (Best Paper). Stanford, UC Berkeley. We propose a fully computational approach for modeling the structure in the space of visual tasks.
Not Applicable
$
8.94
