An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks

Mateusz Kozinski
  • Fonction : Auteur
  • PersonId : 1036104
Loïc Simon

Résumé

We propose a method for semi-supervised training of structured-output neural networks. Inspired by the framework of Generative Adversarial Networks (GAN), we train a discriminator to capture the notion of a 'quality' of network output. To this end, we leverage the qualitative difference between outputs obtained on labelled training data and unannotated data. The discriminator serves as a source of error signal for unlabelled data. Initial experiments in image segmentation demonstrate that including unlabelled data with the proposed loss function into the training procedure enables attaining the same network performance as in a fully supervised scenario, while using two times less annotations.
Fichier principal
Vignette du fichier
adversarial-regularisation-nips.pdf (213.59 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01713323 , version 1 (20-02-2018)

Identifiants

  • HAL Id : hal-01713323 , version 1

Citer

Mateusz Kozinski, Frédéric Jurie, Loïc Simon. An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks. NIPS2017, Dec 2017, Long Beach, United States. ⟨hal-01713323⟩
269 Consultations
144 Téléchargements

Partager

Gmail Facebook X LinkedIn More