A baseline regularization scheme for transfer learning with convolutional neural networks - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Année : 2020

A baseline regularization scheme for transfer learning with convolutional neural networks

Résumé

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which are at least partially relevant for solving the target task, but would be difficult to extract from the limited amount of data available on the target task. However, besides the initialization with the pre-trained model and the early stopping, there is no mechanism in fine-tuning for retaining the features learned on the source task. In this paper, we investigate several regularization schemes that explicitly promote the similarity of the final solution with the initial model. We show the benefit of having an explicit inductive bias towards the initial model. We eventually recommend that the baseline protocol for transfer learning should rely on a simple $L^2$ penalty using the pre-trained model as a reference.
Fichier principal
Vignette du fichier
pr-journal-preprint.pdf (418.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02315752 , version 1 (14-10-2019)

Identifiants

Citer

Xuhong Li, Yves Grandvalet, Franck Davoine. A baseline regularization scheme for transfer learning with convolutional neural networks. Pattern Recognition, 2020, 98, pp.107049. ⟨10.1016/j.patcog.2019.107049⟩. ⟨hal-02315752⟩
98 Consultations
124 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More