On the trade-off between feature extraction and fine tuning in transfer learning
Tutor / directorGarcia Gasulla, Dario
Document typeMaster thesis
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
Transfer learning is the default solution when using deep learning in image-related tasks, like image classification. When a model has been trained in a large and varied enough dataset, it allows to reuse the visual features that it has learnt for tasks that may have limited training data or environments with limited computational resources. In this work we perform an experimental study on feature extraction and fine-tuning, the two most common transfer learning approaches for image classification. We evaluate the trade-offs of performing a hyperparameter search and the subsequent task with both approaches, in relation to performance, environmental footprint, computational and human involved resources. This work shows the cases in which feature extraction or fine tuning are preferable and proposes a series of recommendations of use for transfer learning, with respect to the aforementioned metrics.
SubjectsArtificial intelligence, Deep learning, Neural networks (Computer science), Intel·ligència artificial, Aprenentatge profund, Xarxes neuronals (Informàtica)
DegreeMÀSTER UNIVERSITARI EN INTEL·LIGÈNCIA ARTIFICIAL (Pla 2017)