Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning

Résumé

This paper proposes a step toward obtaining general models of knowledge for facial analysis, by addressing the question of multi-source transfer learning. More precisely, the proposed approach consists in two successive training steps: the first one consists in applying a combination operator to define a common embedding for the multiple sources materialized by different existing trained models. The proposed operator relies on an auto-encoder, trained on a large dataset, efficient both in terms of compression ratio and transfer learning performance. In a second step we exploit a distillation approach to obtain a lightweight student model mimicking the collection of the fused existing models. This model outperforms its teacher on novel tasks, achieving results on par with state-of-the-art methods on 15 facial analysis tasks (and domains), at an affordable training cost. Moreover, this student has 75 times less parameters than the original teacher and can be applied to a variety of novel face-related tasks.
Fichier principal
Vignette du fichier
egpaper_for_review.pdf (731.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02342091 , version 1 (31-10-2019)
hal-02342091 , version 2 (04-11-2019)

Identifiants

Citer

Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux, Frédéric Jurie. Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning. 2019. ⟨hal-02342091v2⟩
95 Consultations
70 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More