Learning with a generative adversarial network from a positive unlabeled dataset for image classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Learning with a generative adversarial network from a positive unlabeled dataset for image classification

Résumé

In this paper, we propose a new approach which addresses the Positive Unlabeled learning challenge for image classification. Its functioning is based on GAN abilities in order to generate fake images samples whose distribution gets closer to negative samples distribution included in the unlabeled dataset available, while being different to the distribution of the unlabeled positive samples. Then we train a CNN classifier with the positive samples and the fake generated samples, as it would be done with a classic Positive Negative dataset. The tests performed on three different image classification datasets show that the system is stable up to an acceptable fraction of positive samples present in the unlabeled dataset. Although very different, this method outperforms the state of the art PU learning on the RGB dataset CIFAR-10.
Fichier principal
Vignette du fichier
Positive-GAN.pdf (470.77 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01811008 , version 1 (08-06-2018)

Identifiants

Citer

F Chiaroni, Mohamed-Cherif Rahal, Nicolas Hueber, Frédéric Dufaux. Learning with a generative adversarial network from a positive unlabeled dataset for image classification. IEEE International Conference on Image Processing (ICIP’2018), Oct 2018, Athens, Greece. ⟨10.1109/icip.2018.8451831⟩. ⟨hal-01811008⟩
267 Consultations
1294 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More