Back to Search
Start Over
Structured Prediction using cGANs with Fusion Discriminator
- Source :
- Workshop on Deep Generative Models for Structured Prediction at ICLR 2019
- Publication Year :
- 2019
-
Abstract
- We propose the fusion discriminator, a single unified framework for incorporating conditional information into a generative adversarial network (GAN) for a variety of distinct structured prediction tasks, including image synthesis, semantic segmentation, and depth estimation. Much like commonly used convolutional neural network -- conditional Markov random field (CNN-CRF) models, the proposed method is able to enforce higher-order consistency in the model, but without being limited to a very specific class of potentials. The method is conceptually simple and flexible, and our experimental results demonstrate improvement on several diverse structured prediction tasks.<br />Comment: 13 pages, 5 figures, 3 tables
Details
- Database :
- arXiv
- Journal :
- Workshop on Deep Generative Models for Structured Prediction at ICLR 2019
- Publication Type :
- Report
- Accession number :
- edsarx.1904.13358
- Document Type :
- Working Paper