Disentanglement by Cyclic Reconstruction - IRT Saint Exupéry - Institut de Recherche Technologique Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Neural Networks and Learning Systems Année : 2022

Disentanglement by Cyclic Reconstruction

Résumé

Deep neural networks have demonstrated their ability to automatically extract meaningful features from data. However, in supervised learning, information specific to the dataset used for training, but irrelevant to the task at hand, may remain encoded in the extracted representations. This remaining information introduces a domain-specific bias, weakening the generalization performance. In this work, we propose splitting the information into a task-related representation and its complementary context representation. We propose an original method, combining adversarial feature predictors and cyclic reconstruction, to disentangle these two representations in the single-domain supervised case. We then adapt this method to the unsupervised domain adaptation problem, consisting of training a model capable of performing on both a source and a target domain. In particular, our method promotes disentanglement in the target domain, despite the absence of training labels. This enables the isolation of task-specific information from both domains and a projection into a common representation. The task-specific representation allows efficient transfer of knowledge acquired from the source domain to the target domain. In the single-domain case, we demonstrate the quality of our representations on information retrieval tasks and the generalization benefits induced by sharpened task-specific representations. We then validate the proposed method on several classical domain adaptation benchmarks and illustrate the benefits of disentanglement for domain adaptation.
Fichier principal
Vignette du fichier
DiCyR_Hal.pdf (4.67 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03501330 , version 1 (23-12-2021)
hal-03501330 , version 2 (29-09-2022)

Licence

Paternité

Identifiants

Citer

David Bertoin, Emmanuel Rachelson. Disentanglement by Cyclic Reconstruction. IEEE Transactions on Neural Networks and Learning Systems, 2022. ⟨hal-03501330v2⟩
51 Consultations
44 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More