no code implementations • 21 Mar 2024 • Gaurav Bhatt, James Ross, Leonid Sigal
Modern pre-trained architectures struggle to retain previous information while undergoing continuous fine-tuning on new tasks.
no code implementations • CVPR 2014 • Demian Wassermann, James Ross, George Washko, William M. Wells III, Raul San Jose-Estepar
Our framework relies on a dense tensor field representation which we implement sparsely as a kernel mixture of tensor fields.