Semantic Segmentation using Adversarial Networks
This work addresses the problem of semantic segmentation for computer vision applications, but it is incremental as it applies an existing adversarial method to a new task.
The paper tackles semantic segmentation by using adversarial training to improve segmentation accuracy, achieving improved results on the Stanford Background and PASCAL VOC 2012 datasets.
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.