Multi-task, Multi-domain Learning: application to semantic segmentation and pose regression

Abstract : We present an approach that leverages multiple datasets annotated for different tasks (e.g., classification with different labelsets) to improve the predictive accuracy on each individual dataset. Domain adaptation techniques can correct dataset bias but they are not applicable when the tasks differ, and they need to be complemented to handle multi-task settings. We propose a new selective loss function that can be integrated into deep neural networks to exploit training data coming from multiple datasets annotated for related but possibly different label sets. We show that the gradient-reversal approach for domain adaptation can be used in this setup to additionally handle domain shifts. We also propose an auto-context approach that further captures existing correlations across tasks. Thorough experiments on two types of applications (semantic segmenta-tion and hand pose estimation) show the relevance of our approach in different contexts.
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger
Contributeur : Damien Fourure <>
Soumis le : mardi 4 juillet 2017 - 12:47:42
Dernière modification le : mercredi 31 octobre 2018 - 12:24:25
Document(s) archivé(s) le : jeudi 14 décembre 2017 - 23:34:34


Fichiers produits par l'(les) auteur(s)



Damien Fourure, Rémi Emonet, Elisa Fromont, Damien Muselet, Natalia Neverova, et al.. Multi-task, Multi-domain Learning: application to semantic segmentation and pose regression. Neurocomputing, Elsevier, 2017, 251, pp.68-80. 〈10.1016/j.neucom.2017.04.014〉. 〈hal-01507132v2〉



Consultations de la notice


Téléchargements de fichiers