Semantic Segmentation using Adversarial Networks - Archive ouverte HAL Access content directly
Conference Papers Year :

Semantic Segmentation using Adversarial Networks

(1, 2) , (2) , (2) , (1)
1
2

Abstract

Adversarial training has been shown to produce state of the art results for generative image modeling. In this paper we propose an adversarial training approach to train semantic segmentation models. We train a convolutional semantic segmentation network along with an adversarial network that discriminates segmentation maps coming either from the ground truth or from the segmentation network. The motivation for our approach is that it can detect and correct higher-order inconsistencies between ground truth segmentation maps and the ones produced by the segmentation net. Our experiments show that our adversarial training approach leads to improved accuracy on the Stanford Background and PASCAL VOC 2012 datasets.
Fichier principal
Vignette du fichier
luc16wat.pdf (2.16 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01398049 , version 1 (23-11-2016)

Identifiers

  • HAL Id : hal-01398049 , version 1

Cite

Pauline Luc, Camille Couprie, Soumith Chintala, Jakob Verbeek. Semantic Segmentation using Adversarial Networks. NIPS Workshop on Adversarial Training, Dec 2016, Barcelona, Spain. ⟨hal-01398049⟩
1564 View
1482 Download

Share

Gmail Facebook Twitter LinkedIn More