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

Mateusz Kozí Nski 1 Loïc Simon 1 Frédéric Jurie 1
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01713323
Contributor : Frederic Jurie <>
Submitted on : Tuesday, February 20, 2018 - 2:25:55 PM
Last modification on : Thursday, February 7, 2019 - 5:36:31 PM
Document(s) archivé(s) le : Monday, May 21, 2018 - 12:52:02 PM

File

adversarial-regularisation-nip...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01713323, version 1

Citation

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

Share

Metrics

Record views

201

Files downloads

162