Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

Published October 20, 2022 | Version v1
Conference paper Open

When & How to Transfer with Transfer Learning

  • 1. Barcelona Supercomputing Center

Description

In deep learning, transfer learning (TL) has become the de facto approach when dealing with image related tasks. Visual features learnt for one task have been shown to be reusable for other tasks, improving performance significantly. By reusing deep representations, TL enables the use of deep models in domains with limited data availability, limited computational resources and/or limited access to human experts. Domains which include the vast majority of real-life applications. This paper conducts an experimental evaluation of TL, exploring its trade-offs with respect to performance, environmental footprint, human hours and computational requirements. Results highlight the cases were a cheap feature extraction approach is preferable, and the situations where an expensive fine-tuning effort may be worth the added cost. Finally, a set of guidelines on the use of TL are proposed.

Files

Transfer_Learning_Tradeoff_NIPS_Workshop_22_preprint.pdf

Files (174.5 kB)

Additional details

Funding

AI4Media – A European Excellence Centre for Media, Society and Democracy 951911
European Commission