Semantic Segmentation using Adversarial Networks

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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [34 references]  Display  Hide  Download

https://hal.inria.fr/hal-01398049
Contributor : Thoth Team <>
Submitted on : Wednesday, November 23, 2016 - 2:18:46 PM
Last modification on : Monday, April 30, 2018 - 3:02:01 PM
Document(s) archivé(s) le : Monday, March 20, 2017 - 10:38:38 PM

File

luc16wat.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01398049, version 1

Collections

Citation

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

Share

Metrics

Record views

1444

Files downloads

1279