Authors: Linchao Zhu, Sercan O. Arik, Yi Yang, and Tomas Pfister
Paper: https://arxiv.org/abs/1908.11406
Learning to transfer learn (L2TL), to improve transfer learning on a target dataset by judicious extraction of information from a source dataset.
This repository contains an example implementation of L2TL framework on the task of transferring knowledge from MNIST to SVHN.
To run the experiments that compare training from random initialization, fine-tuning and L2TL, run bash all_experiments.sh.