Which Model to Transfer Finding the Needle in the Growing Haystack

Transfer learning has been popularized as a data-efficient alternative to training models from scratch . The emergence of rich model repositories, such as TensorFlow Hub, enables the practitioners and researchers to unleash the potential of these models across a wide range of downstream tasks . We conduct a large-scale empirical study and show that both task-agnostic and task-aware methods can yield high regret . We then propose a simple and computationally efficient hybrid search strategy which outperforms the existing approaches . We highlight the practical benefits of the proposed solution on a set of 19 diverse vision tasks. We then present a simple, computationally . effective hybrid search solution to the problem of selecting a good model for the task at hand. It is possible to use a model for a particular vision task to solve the problem in the future.

Links: PDF - Abstract

Code :


Keywords : model - task - solution - tasks - transfer -

Leave a Reply

Your email address will not be published. Required fields are marked *