When & How to Transfer with Transfer Learning
It provides practical guidelines for applying TL in real-life applications with limited data, computation, or expertise, though it is incremental as it builds on existing TL methods.
This paper experimentally evaluates transfer learning (TL) for image tasks, identifying when cheap feature extraction is preferable versus when expensive fine-tuning is worth the cost, based on trade-offs in performance, environmental footprint, human hours, and computational requirements.
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.