Skip to Main content Skip to Navigation
Conference papers

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
Complete list of metadata

Cited literature [34 references]  Display  Hide  Download
Contributor : Thoth Team Connect in order to contact the contributor
Submitted on : Wednesday, November 23, 2016 - 2:18:46 PM
Last modification on : Wednesday, November 3, 2021 - 8:30:00 AM
Long-term archiving on: : Monday, March 20, 2017 - 10:38:38 PM


Files produced by the author(s)


  • HAL Id : hal-01398049, version 1



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



Les métriques sont temporairement indisponibles